© 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. 92095
    Prev
    Next
    INDEX
    Explanations

    Mot

    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
    es
    -0.78
    alia
    -0.69
     mot
    -0.64
    cic
    -0.63
    lose
    -0.59
    ES
    -0.59
     personal
    -0.58
    mal
    -0.57
    ing
    -0.57
    ,
    -0.57
    POSITIVE LOGITS
    TagMode
    0.75
     ModelExpression
    0.69
    ParallelGroup
    0.66
    ंदीखरीदारी
    0.63
     createSlice
    0.63
    testens
    0.62
     <>",
    0.62
    WebMethod
    0.61
    tonode
    0.60
    lapsingToolbar
    0.59
    Activations Density 1.052%

    No Known Activations