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. 5-CLT-HP
    4. 1781
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    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
    Hochspringen
    -0.92
     Cæsar
    -0.84
     تعدى
    -0.79
     ſeveral
    -0.79
    TagMode
    -0.79
     Monfieur
    -0.77
     Anſ
    -0.77
     MotionEvent
    -0.77
     itſelf
    -0.77
     reaſon
    -0.77
    POSITIVE LOGITS
     deb
    0.44
    whip
    0.42
     Ren
    0.42
     of
    0.42
     ظ
    0.42
     leg
    0.40
    .
    0.40
     dep
    0.39
    (
    0.39
    @
    0.38
    Activations Density 0.136%

    No Known Activations