© 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. 90934
    Prev
    Next
    INDEX
    Explanations

    attack

    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
    GenerationType
    -0.60
     AssemblyCulture
    -0.60
    \{\\
    -0.55
    __":
    -0.54
     виправивши
    -0.54
    aarrggbb
    -0.54
    كومة
    -0.52
    PhysRevD
    -0.51
    帖最后由
    -0.50
     ran
    -0.49
    POSITIVE LOGITS
    localPosition
    0.58
    ThroughAttribute
    0.56
    ถึง
    0.52
     nastro
    0.50
     patho
    0.50
     asupra
    0.50
    putra
    0.50
    strijd
    0.49
     ++)
    0.49
    Atsauces
    0.49
    Activations Density 0.002%

    No Known Activations