© 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. 1015
    Prev
    Next
    INDEX
    Explanations

    variety of internet content

    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
     AppColors
    -0.60
    出版年
    -0.51
     */;
    -0.47
     behavioural
    -0.44
    
    -0.42
    ReusableCell
    -0.41
    SError
    -0.41
     sī
    -0.41
    tvguidetime
    -0.41
     Behavioural
    -0.40
    POSITIVE LOGITS
    FTFY
    0.57
    Demografia
    0.57
    ngrx
    0.57
    <bos>
    0.56
    الدراسه
    0.56
     whoſe
    0.55
    BASELINE
    0.55
    browserify
    0.54
    Lieferumfang
    0.52
    بوابة
    0.52
    Activations Density 0.001%

    No Known Activations