© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10802
    Prev
    Next
    INDEX
    Explanations

    Suffixes

    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
    setVerticalGroup
    -0.72
    
    -0.69
     resourceCulture
    -0.60
    RegressionTest
    -0.60
    BufferException
    -0.59
    oredCriteria
    -0.56
    GraphicsUnit
    -0.52
    期刊论文
    -0.50
    estars
    -0.49
     jspb
    -0.49
    POSITIVE LOGITS
     referenties
    0.71
    <bos>
    0.68
     itſelf
    0.63
     Monfieur
    0.60
    '
    0.59
     themſelves
    0.59
    '}>
    0.59
     himſelf
    0.58
     Jefus
    0.57
     ProtoMessage
    0.57
    Activations Density 0.279%

    No Known Activations