© 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. 91406
    Prev
    Next
    INDEX
    Explanations

    gaining access

    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
     חיצוניים
    -0.56
     digitais
    -0.48
     sanitaires
    -0.47
     esser
    -0.47
     ficando
    -0.45
     hjemmeside
    -0.43
    AndEndTag
    -0.43
     présentes
    -0.43
    setStroke
    -0.42
    IndentedString
    -0.42
    POSITIVE LOGITS
    ValueStyle
    0.82
     Constantinople
    0.58
     Wicidata
    0.58
     newBuilder
    0.57
     onCreateView
    0.57
    AtIndexPath
    0.56
     cultivate
    0.54
    posedge
    0.54
    addPreferredGap
    0.54
     Chrift
    0.53
    Activations Density 0.003%

    No Known Activations