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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 718
    Prev
    Next
    INDEX
    Explanations

    new releases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SBATCH
    -0.77
     resourceCulture
    -0.62
     Winaray
    -0.61
    Pratique
    -0.58
     بيها
    -0.57
     autorytatywna
    -0.57
    CloseOperation
    -0.56
    InvalidProtocol
    -0.55
    ↩
    -0.54
    ofType
    -0.54
    POSITIVE LOGITS
    <bos>
    0.66
     today
    0.63
     confirm
    0.60
     out
    0.53
     reinforce
    0.52
     join
    0.51
     strengthen
    0.51
     mean
    0.50
     continue
    0.49
     call
    0.49
    Activations Density 0.008%

    No Known Activations