© 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. 5-CLT-HP
    7. 90974
    Prev
    Next
    INDEX
    Explanations

    all

    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
    Negative Logits
    saraba
    -0.74
    /**
    -0.71
    AndEndTag
    -0.68
    ]--;
    -0.66
    memoized
    -0.66
     specific
    -0.66
    BindView
    -0.65
     Shining
    -0.64
    oshin
    -0.63
     nakalista
    -0.63
    POSITIVE LOGITS
     gång
    0.40
     season
    0.39
     للمعارف
    0.38
    llllllll
    0.34
     musim
    0.33
     Roskov
    0.33
     vigencia
    0.33
    
    0.33
     mesmas
    0.32
     ouver
    0.32
    Activations Density 0.001%

    No Known Activations