© 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. 408
    Prev
    Next
    INDEX
    Explanations

    the word "haven't" or "haven" combined with a verb following it

    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
    50
    +0.07
    0.3%
    1921
    +0.07
    0.2%
    478
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    601
    +0.07
    0.03
    74
    +0.07
    0.03
    2038
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.20
    ੁ
    -0.69
    ਿੱ
    -0.68
    ⓧ
    -0.64
    /*
    -0.63
    ///**
    -0.61
    fektions
    -0.61
    ///
    -0.60
     attend
    -0.60
    //}
    -0.59
    POSITIVE LOGITS
     affor
    1.84
     maneu
    1.83
     aen
    1.74
     increa
    1.74
     haven
    1.73
     impra
    1.72
     secon
    1.70
     guarante
    1.67
     mef
    1.67
     emphat
    1.65
    Activations Density 0.110%

    No Known Activations