© 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. 45181
    Prev
    Next
    INDEX
    Explanations

    safety

    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
     zelve
    -1.16
     feroit
    -1.13
     auroit
    -1.05
     avoient
    -1.04
     ſmall
    -1.04
    IsMutable
    -1.03
     sauvages
    -1.01
     pouvoit
    -1.00
     houſe
    -0.99
     étoit
    -0.98
    POSITIVE LOGITS
    ↵
    0.50
      
    0.46
     bo
    0.46
     b
    0.45
    le
    0.45
     ply
    0.45
    les
    0.44
     mat
    0.44
     touch
    0.43
     ma
    0.43
    Activations Density 0.478%

    No Known Activations