© 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. 4-CLT-HP
    7. 4376
    Prev
    Next
    INDEX
    Explanations

    Gray

    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
     bParam
    -0.50
    DeleteBehavior
    -0.46
    instancetype
    -0.46
    choc
    -0.44
     sug
    -0.44
     Hump
    -0.44
    icon
    -0.41
     bumb
    -0.40
    ')(
    -0.39
     sam
    -0.39
    POSITIVE LOGITS
    aarrggbb
    0.63
    Digitized
    0.56
    erville
    0.56
     nemlig
    0.56
     कैसी
    0.55
    ViewFeatures
    0.54
    awaiter
    0.54
    -------
    0.53
    ρίζ
    0.53
    #+#
    0.53
    Activations Density 0.007%

    No Known Activations