© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95443
    Prev
    Next
    INDEX
    Explanations

    destruction and fragility

    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
     snippetHide
    -1.09
    thâu
    -1.08
     فريبيس
    -1.02
     Efq
    -0.97
     שוליים
    -0.95
    rungsseite
    -0.94
    
    -0.92
     doubtnut
    -0.91
    StoryboardSegue
    -0.91
     auroit
    -0.88
    POSITIVE LOGITS
    s
    0.60
    e
    0.54
    a
    0.49
     U
    0.48
     in
    0.47
     "
    0.46
     serious
    0.44
     by
    0.44
    ی
    0.44
     (
    0.43
    Activations Density 0.113%

    No Known Activations