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. 1911
    Prev
    Next
    INDEX
    Explanations

    use of examples

    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
    setVerticalGroup
    -0.93
     myſelf
    -0.91
     reaſon
    -0.88
     Houſe
    -0.87
     purpoſe
    -0.85
     Anſ
    -0.84
     houſe
    -0.84
     Reſ
    -0.82
     Majefty
    -0.81
     juſ
    -0.81
    POSITIVE LOGITS
     externos
    0.44
     një
    0.43
     défi
    0.43
    pí
    0.40
     to
    0.40
     mulig
    0.40
     tambahan
    0.38
     về
    0.37
    hilangan
    0.37
     একটি
    0.37
    Activations Density 0.005%

    No Known Activations