© 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. 4306
    Prev
    Next
    INDEX
    Explanations

    silken

    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
    ChildIndex
    -0.65
     Italijanski
    -0.50
     }{@
    -0.49
    TypeDef
    -0.49
     Roskov
    -0.49
    rovna
    -0.48
    OwnProperty
    -0.48
    ompi
    -0.47
    nologies
    -0.47
     ActivatedRoute
    -0.46
    POSITIVE LOGITS
     intptr
    0.63
    
    0.61
    -------------</
    0.59
    ']>
    0.54
    stare
    0.54
     tetto
    0.54
    ]--;
    0.54
    )++;
    0.52
    isNameExpr
    0.52
    hearted
    0.51
    Activations Density 0.009%

    No Known Activations