© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73782
    Prev
    Next
    INDEX
    Explanations

    Actions/Verbs

    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
    IsContent
    -0.78
    LookAnd
    -0.63
     esternos
    -0.60
     Lightboxes
    -0.54
     Exacts
    -0.53
    Demografie
    -0.53
    Expose
    -0.52
    ⓧ
    -0.52
     aque
    -0.52
    Preserve
    -0.51
    POSITIVE LOGITS
     go
    0.77
     cross
    0.73
    OrBuilder
    0.60
     come
    0.58
     sleep
    0.58
     jump
    0.58
    stand
    0.57
     stand
    0.57
     sit
    0.55
    cross
    0.54
    Activations Density 0.005%

    No Known Activations