© 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. 20-CLT-HP
    7. 73104
    Prev
    Next
    INDEX
    Explanations

    Halloween

    np_max-act-logits · 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
    ENDIAN
    -0.60
     Référence
    -0.56
     Meilleur
    -0.55
    Thanksgiving
    -0.54
    September
    -0.54
    avajillas
    -0.53
    Endian
    -0.53
    anguard
    -0.52
    Примечания
    -0.52
    knecht
    -0.51
    POSITIVE LOGITS
     g
    0.82
    enumi
    0.65
    BufferException
    0.57
     jack
    0.55
     cob
    0.53
     fri
    0.52
     All
    0.50
    gh
    0.49
     NgModule
    0.49
     BorderSide
    0.48
    Activations Density 0.011%

    No Known Activations