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. 0-CLT-HP
    4. 294
    Prev
    Next
    INDEX
    Explanations

    AppCompat

    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
     enf
    -0.48
    |+\
    -0.47
    ↵↵
    -0.46
    ま
    -0.46
    QRST
    -0.45
    béco
    -0.44
     lot
    -0.44
    mente
    -0.44
    ↵
    -0.43
    予
    -0.42
    POSITIVE LOGITS
    Personensuche
    0.91
    IndentedString
    0.89
    tagHelperRunner
    0.77
     ModelExpression
    0.75
    ⓧ
    0.74
     OFDb
    0.73
    ThroughAttribute
    0.73
    TypedDataSet
    0.72
    XmlAccessType
    0.72
    udahkan
    0.71
    Activations Density 0.106%

    No Known Activations