© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15413
    Prev
    Next
    INDEX
    Explanations

    Loss/destruction/problems

    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
     pstmt
    -0.56
    Rè
    -0.54
    ≦)
    -0.54
     linkovi
    -0.54
    יוחד
    -0.54
    Numerology
    -0.52
     sebaliknya
    -0.50
    esercito
    -0.50
    ræ
    -0.49
    Referensi
    -0.49
    POSITIVE LOGITS
     AssemblyTitle
    0.61
    awtextra
    0.57
     defaultstate
    0.56
    SourceChecksum
    0.56
    isome
    0.54
    ThroughAttribute
    0.52
    \{\\
    0.52
     IndexPath
    0.50
     AspNetCore
    0.50
    فحة
    0.50
    Activations Density 0.019%

    No Known Activations