© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39916
    Prev
    Next
    INDEX
    Explanations

    scientific/technical documents

    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
    __':
    
    -0.97
    __":
    
    -0.82
    Билгалдахарш
    -0.80
    <bos>
    -0.66
    _
    
    -0.66
    ItemBackground
    -0.64
    '):
    
    -0.63
    ()?;
    -0.63
    "]);
    
    -0.62
    '>
    
    -0.58
    POSITIVE LOGITS
    .
    0.74
    ,
    0.69
    ;
    0.63
    :
    0.54
     would
    0.50
     relates
    0.48
     alleges
    0.48
     might
    0.47
     cannot
    0.47
     propios
    0.47
    Activations Density 0.033%

    No Known Activations