Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12639
    Prev
    Next
    INDEX
    Explanations

    the

    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
     beginnetje
    -0.50
    from
    -0.45
    NullException
    -0.44
    aur
    -0.44
    InstrumentedTest
    -0.43
    thal
    -0.42
    ape
    -0.42
    putAll
    -0.42
    urat
    -0.41
    Jsp
    -0.40
    POSITIVE LOGITS
    uxxxx
    0.72
    LLocation
    0.68
    IsContent
    0.62
    skjaer
    0.60
     nuns
    0.59
    Espèce
    0.58
    providedIn
    0.58
     fieldNum
    0.57
     Dollars
    0.56
    addCriterion
    0.56
    Activations Density 0.092%

    No Known Activations