© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 646
    Prev
    Next
    INDEX
    Explanations

    terms related to sports competitions and awards, particularly focusing on MVP (Most Valuable Player) awards

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1909
    +0.08
    0.3%
    938
    +0.08
    0.3%
    545
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.08
    0.03
    12
    +0.08
    0.02
    938
    +0.08
    0.02
    Negative Logits
    glEnable
    -0.64
    cur
    -0.61
    হ
    -0.59
    public
    -0.56
     cur
    -0.55
    /**
    -0.54
    /**
    -0.53
    void
    -0.53
    ोंने
    -0.52
    حث
    -0.52
    POSITIVE LOGITS
     MVP
    2.00
    MVP
    1.74
     stockholm
    1.39
     alaska
    1.35
     scrat
    1.29
     accla
    1.29
     seoul
    1.26
     emphat
    1.26
     strick
    1.23
     wien
    1.19
    Activations Density 0.172%

    No Known Activations