© 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. 5-CLT-HP
    7. 5693
    Prev
    Next
    INDEX
    Explanations

    s

    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
    SharedDtor
    -0.76
    rungsseite
    -0.68
     protoimpl
    -0.68
     समीक्षक
    -0.64
    elemField
    -0.60
     незавершена
    -0.58
     utafitiHapana
    -0.57
    bolista
    -0.57
    oa̍t
    -0.56
     études
    -0.56
    POSITIVE LOGITS
     and
    0.59
     or
    0.57
     StatelessWidget
    0.55
     voluntarily
    0.52
     agree
    0.52
     disagree
    0.52
    ́ng
    0.50
    TouchEvent
    0.50
    inander
    0.49
     coordinate
    0.49
    Activations Density 0.000%

    No Known Activations