© 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. 44118
    Prev
    Next
    INDEX
    Explanations

    Judge

    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
     Judge
    -0.75
    Judge
    -0.69
    __':
    -0.64
     hosted
    -0.64
    bot
    -0.61
    a
    -0.60
    <bos>
    -0.60
     cherchés
    -0.59
     moderated
    -0.56
    addCriterion
    -0.56
    POSITIVE LOGITS
     themſelves
    0.61
    hoeddwyd
    0.58
     numberWith
    0.57
     myſelf
    0.57
    ilant
    0.56
     Theſe
    0.55
     Houſe
    0.55
    IGR
    0.54
     Gorb
    0.53
     swarming
    0.53
    Activations Density 1.785%

    No Known Activations