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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 243
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the concept of "freedom"

    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%
    1092
    +0.07
    0.3%
    1506
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1219
    +0.07
    0.03
    543
    +0.07
    0.03
    1128
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.37
    /*
    -0.89
    /**
    -0.80
    public
    -0.75
    /*
    -0.74
    
    -0.73
    //
    -0.71
    #
    -0.70
    ,
    -0.68
    .
    -0.67
    POSITIVE LOGITS
     freedom
    2.10
     Freedom
    2.10
     FREEDOM
    2.07
    freedom
    2.00
    Freedom
    1.96
     Minang
    1.91
     affor
    1.88
     accla
    1.88
     stockholm
    1.88
     bandung
    1.84
    Activations Density 0.120%

    No Known Activations