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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12054
    Prev
    Next
    INDEX
    Explanations

    arson

    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
    arton
    -0.73
    anton
    -0.69
     Arca
    -0.58
    дравству
    -0.56
    tones
    -0.56
    lars
    -0.56
    AddWithValue
    -0.56
    toml
    -0.56
    gai
    -0.54
     Cavalry
    -0.54
    POSITIVE LOGITS
    StructEnd
    0.53
     autorytatywna
    0.46
     ویکی‌پدیای
    0.41
    WebMethod
    0.41
    MENAFN
    0.40
    yszcz
    0.39
     CWE
    0.39
     <=",
    0.38
    Œuvres
    0.37
    المناصب
    0.37
    Activations Density 0.230%

    No Known Activations