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. 5-CLT-HP
    4. 95952
    Prev
    Next
    INDEX
    Explanations

    code

    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
    avax
    -1.57
    findpost
    -0.74
    RegressionTest
    -0.73
     الدولى
    -0.73
    featureID
    -0.71
     Audiodateien
    -0.70
     AssemblyTitle
    -0.69
    GraphicsUnit
    -0.66
    ureusement
    -0.66
    ChildScrollView
    -0.66
    POSITIVE LOGITS
    U
    0.54
     U
    0.49
    Rico
    0.45
     Bellevue
    0.43
     Plugin
    0.42
     Data
    0.41
     UID
    0.40
    lex
    0.40
     leverage
    0.40
    (@"
    0.40
    Activations Density 0.002%

    No Known Activations