© 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. 0-CLT-HP
    7. 1083
    Prev
    Next
    INDEX
    Explanations

    ifts

    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
    rata
    -0.96
    dition
    -0.83
    ThroughAttribute
    -0.71
    vention
    -0.70
    ition
    -0.68
    marks
    -0.66
    IsMutable
    -0.65
    shan
    -0.65
    isher
    -0.64
    ITION
    -0.63
    POSITIVE LOGITS
    enumi
    0.58
     lenger
    0.56
    Datuak
    0.55
    icznego
    0.54
    quisites
    0.53
     Noble
    0.51
    Geplaatst
    0.50
     سكانية
    0.49
    にほんブログ村
    0.49
    Jîn
    0.48
    Activations Density 0.157%

    No Known Activations