© 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. 1-CLT-HP
    7. 9655
    Prev
    Next
    INDEX
    Explanations

    damage and repair

    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
    <bos>
    -0.65
     gainera
    -0.55
     anledning
    -0.54
    writerow
    -0.49
    zema
    -0.47
    Sums
    -0.46
    KindOfClass
    -0.43
    stwie
    -0.43
    KommentareTeilen
    -0.43
    /$',
    -0.43
    POSITIVE LOGITS
    >//
    0.57
     surla
    0.56
    MemoryWarning
    0.56
    __*/
    0.54
    gatsby
    0.54
     caused
    0.54
    extAlignment
    0.54
     travellers
    0.53
     travelers
    0.53
    ContentAsync
    0.53
    Activations Density 0.046%

    No Known Activations