© 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. 96279
    Prev
    Next
    INDEX
    Explanations

    "form of"

    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
     ног
    -0.44
    .
    -0.42
     he
    -0.42
     trend
    -0.42
     pushes
    -0.40
     pays
    -0.39
     indication
    -0.39
    ↵↵
    -0.39
    mula
    -0.39
     lends
    -0.38
    POSITIVE LOGITS
     Biôgrafia
    0.75
    interopRequire
    0.72
     مشين
    0.72
    AndEndTag
    0.72
    PRNewswire
    0.71
    IContainer
    0.69
     ostavi
    0.69
     }{@
    0.68
    躇
    0.67
    COUVER
    0.66
    Activations Density 0.002%

    No Known Activations