© 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. 5-CLT-HP
    7. 96213
    Prev
    Next
    INDEX
    Explanations

    surfaces

    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
    <bos>
    -0.45
    ly
    -0.43
    tioner
    -0.43
    namn
    -0.42
     untere
    -0.42
    Categor
    -0.42
    جات
    -0.42
     Normdatei
    -0.41
    rie
    -0.41
    لينكات
    -0.41
    POSITIVE LOGITS
     lenker
    0.95
    ChildScrollView
    0.70
     SafeMath
    0.70
    Спољашње
    0.69
    UnusedPrivate
    0.68
     linkovi
    0.66
     jspb
    0.65
    ">//
    0.63
    ViewFeatures
    0.61
     fieldNum
    0.61
    Activations Density 0.003%

    No Known Activations