© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1061
    Prev
    Next
    INDEX
    Explanations

    "using"

    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
    بوابة
    -0.54
    цездатний
    -0.54
     FRANCISCO
    -0.51
     aceptas
    -0.49
    Filmography
    -0.47
    StreetMap
    -0.46
    djangoproject
    -0.45
     accepted
    -0.44
     cương
    -0.44
    PointerException
    -0.44
    POSITIVE LOGITS
    WriteLiteral
    0.71
     kasarigan
    0.69
    endregion
    0.63
    GetAsync
    0.59
    出版年
    0.58
    acies
    0.57
     pinulongan
    0.57
     defaultstate
    0.57
    paku
    0.57
     kaarangay
    0.56
    Activations Density 0.005%

    No Known Activations