© 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. 72208
    Prev
    Next
    INDEX
    Explanations

    Code/Technical Documents

    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
    bootstrapcdn
    -0.54
    vég
    -0.52
     voud
    -0.52
     elä
    -0.52
     Freeway
    -0.50
    างเกง
    -0.50
    ductory
    -0.49
    colar
    -0.49
     Edmonds
    -0.48
     informée
    -0.48
    POSITIVE LOGITS
    ########.
    0.66
    tagHelperRunner
    0.63
    featureID
    0.59
    
    0.59
    findpost
    0.58
     kasarigan
    0.55
    __*/
    0.53
    uxxxx
    0.52
    SerializedName
    0.51
     kaarangay
    0.50
    Activations Density 0.003%

    No Known Activations