© 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. 1-CLT-HP
    7. 543
    Prev
    Next
    INDEX
    Explanations

    7

    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
    7
    -0.84
    ContentAlignment
    -0.82
     /\.(
    -0.81
    WireFormatLite
    -0.81
    ValueStyle
    -0.79
    saraba
    -0.76
    OGND
    -0.76
     seventh
    -0.74
     seven
    -0.69
     Seven
    -0.69
    POSITIVE LOGITS
     Mä
    0.46
    Mixin
    0.46
     pistola
    0.44
     Rot
    0.41
    …………………………………………
    0.41
     affair
    0.40
    放过
    0.39
    nA
    0.39
     Complex
    0.37
    さま
    0.37
    Activations Density 0.054%

    No Known Activations