© 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. 20-CLT-HP
    7. 76812
    Prev
    Next
    INDEX
    Explanations

    trying

    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
     utafitiHapana
    -0.85
    AndEndTag
    -0.62
    featureID
    -0.59
     Numerade
    -0.56
    styleType
    -0.54
    AccessorTable
    -0.53
    ########.
    -0.50
    TintMode
    -0.50
    localctx
    -0.50
    SourceChecksum
    -0.48
    POSITIVE LOGITS
     direct
    0.63
     facie
    0.58
    Kaynakça
    0.57
    
    0.56
     drive
    0.55
     move
    0.52
     walk
    0.52
     direkte
    0.51
    direct
    0.51
     call
    0.50
    Activations Density 0.001%

    No Known Activations