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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 263
    Prev
    Next
    INDEX
    Explanations

    s

    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
    antMatchers
    -0.55
    %}
    -0.55
     utafitiHapana
    -0.54
    ondheim
    -0.50
    RegistryLite
    -0.48
     Lawn
    -0.48
    viewDid
    -0.47
    ification
    -0.45
     skry
    -0.44
    LLOW
    -0.44
    POSITIVE LOGITS
    IsContent
    0.63
     AssemblyCulture
    0.59
    requestCode
    0.57
    InvalidProtocol
    0.56
    fillType
    0.54
    ’
    0.53
    MessageOf
    0.52
    writeField
    0.52
    ruptedException
    0.50
    Javadoc
    0.50
    Activations Density 0.026%

    No Known Activations