© 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. 92013
    Prev
    Next
    INDEX
    Explanations

    Conversational text

    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
     traces
    -0.88
    evidence
    -0.78
     preuves
    -0.77
     myſelf
    -0.77
     feroit
    -0.75
     étoient
    -0.75
     pleaſure
    -0.75
     Traces
    -0.74
     auroit
    -0.73
     avoient
    -0.73
    POSITIVE LOGITS
     of
    0.72
    ous
    0.61
     
    0.57
    .
    0.54
    ,
    0.53
     after
    0.52
    ValueStyle
    0.52
     bad
    0.52
      
    0.51
    OUS
    0.50
    Activations Density 0.024%

    No Known Activations