© 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. 5834
    Prev
    Next
    INDEX
    Explanations

    throne

    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
    UnknownFields
    -0.52
     @"";
    -0.50
     AGENDA
    -0.50
    っこう
    -0.50
    StructEnd
    -0.49
    latego
    -0.49
    interopRequire
    -0.48
    دانشنامهٔ
    -0.48
     tslint
    -0.47
     nicio
    -0.47
    POSITIVE LOGITS
     Reverso
    0.56
    Parcelize
    0.55
     poveznice
    0.54
    featureID
    0.53
     gainera
    0.51
    mphony
    0.49
     Peers
    0.48
    Datuak
    0.47
    OwnProperty
    0.46
     spann
    0.46
    Activations Density 0.002%

    No Known Activations