© 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. 5-CLT-HP
    7. 91589
    Prev
    Next
    INDEX
    Explanations

    direct

    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
    ništ
    -0.49
    extAlignment
    -0.46
     bParam
    -0.45
    tiglia
    -0.45
     nahilalakip
    -0.43
    setVerticalGroup
    -0.43
    жих
    -0.43
    PROLOG
    -0.42
    Aiheesta
    -0.41
    zels
    -0.41
    POSITIVE LOGITS
     Usage
    0.55
    DockStyle
    0.55
     poveznice
    0.54
     datter
    0.54
     translation
    0.53
    Immediate
    0.52
     genitori
    0.52
    writeFieldEnd
    0.52
    Strengths
    0.52
     referenties
    0.52
    Activations Density 0.001%

    No Known Activations