© 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. 45829
    Prev
    Next
    INDEX
    Explanations

    rate

    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
     resourceCulture
    -0.89
     ModelExpression
    -0.75
     Infórmanos
    -0.68
    +:+
    -0.67
    ⓧ
    -0.65
    tagHelperRunner
    -0.61
     autorytatywna
    -0.60
    webElementXpaths
    -0.60
     cherchés
    -0.59
     transfieras
    -0.59
    POSITIVE LOGITS
     estekak
    0.54
    Hallo
    0.49
    argout
    0.46
    حياتها
    0.46
     بیر
    0.44
    celes
    0.44
     INVENTION
    0.44
    \{\\
    0.43
    EINVAL
    0.42
     Bielefeld
    0.42
    Activations Density 0.035%

    No Known Activations