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. 20-CLT-HP
    4. 73823
    Prev
    Next
    INDEX
    Explanations

    anti

    np_max-act-logits · 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
    NUMX
    -0.59
    OrEqualTo
    -0.56
    sizeCache
    -0.54
    ,:),
    -0.52
    :+:
    -0.52
    WireFormatLite
    -0.51
     sqft
    -0.50
    nodoc
    -0.50
    ,:,
    -0.50
     IActionResult
    -0.49
    POSITIVE LOGITS
    moine
    0.48
    Water
    0.42
    Growing
    0.41
    lasty
    0.41
    chrift
    0.40
    Mutation
    0.40
    Mama
    0.39
    tomi
    0.38
     htmlFor
    0.38
    menta
    0.38
    Activations Density 0.000%

    No Known Activations