© 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. 1-CLT-HP
    7. 45684
    Prev
    Next
    INDEX
    Explanations

    Almost

    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
    __*/
    -0.76
     engraçadas
    -0.72
    ftagPool
    -0.70
    |}{$
    -0.69
    bkz
    -0.68
    ✨:
    -0.67
    étoit
    -0.65
    󠁢
    -0.65
    kloped
    -0.65
    rawDesc
    -0.63
    POSITIVE LOGITS
    <bos>
    1.09
     
    0.72
    ,
    0.52
      
    0.52
    <strong>
    0.49
    <b>
    0.47
     in
    0.47
    ↵
    0.46
    '
    0.45
     so
    0.45
    Activations Density 0.621%

    No Known Activations