© 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. 0-CLT-HP
    7. 39845
    Prev
    Next
    INDEX
    Explanations

    preference

    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
     prefer
    -1.59
     preferred
    -1.53
     Prefer
    -1.53
    prefer
    -1.45
    Prefer
    -1.42
    preferred
    -1.40
     prefers
    -1.39
     Preferred
    -1.34
    Preferred
    -1.25
    ideal
    -1.18
    POSITIVE LOGITS
     to
    0.58
     convincing
    0.50
     purchasing
    0.49
    going
    0.49
     buying
    0.47
     morning
    0.46
     going
    0.45
     doing
    0.45
    imeter
    0.44
    κτή
    0.44
    Activations Density 0.434%

    No Known Activations