© 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. 2009
    Prev
    Next
    INDEX
    Explanations

    speaking

    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
     resourceCulture
    -0.82
     kasarigan
    -0.63
     препратки
    -0.54
    intele
    -0.53
    Erreferentziak
    -0.52
    protoc
    -0.51
    AntiForgeryToken
    -0.48
    CodedInputStream
    -0.47
    multer
    -0.47
    बाह
    -0.46
    POSITIVE LOGITS
     French
    0.61
     English
    0.61
     Arabic
    0.57
     Púb
    0.55
     Spanish
    0.55
    InitVars
    0.54
     Dutch
    0.54
     Italian
    0.52
     German
    0.52
    French
    0.51
    Activations Density 0.001%

    No Known Activations