© 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. 20-CLT-HP
    7. 75382
    Prev
    Next
    INDEX
    Explanations

    separation

    np_max-act-logits · 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
     للاسماء
    -0.77
    sidemargin
    -0.70
    InjectAttribute
    -0.69
     gynhyrchwyd
    -0.68
     nakalista
    -0.68
    RegressionTest
    -0.66
    ResumeLayout
    -0.65
    enderror
    -0.63
    DebuggerNonUser
    -0.62
     mergeFrom
    -0.61
    POSITIVE LOGITS
     separation
    0.60
    Separation
    0.59
     Separation
    0.56
     séparation
    0.50
     separa
    0.50
    aarrggbb
    0.50
     divid
    0.50
     Par
    0.49
    arate
    0.48
    cèse
    0.47
    Activations Density 0.000%

    No Known Activations