© 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. 1-CLT-HP
    7. 15414
    Prev
    Next
    INDEX
    Explanations

    structure and concentration

    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
     cebolla
    -0.53
     jScrollPane
    -0.50
     musiciens
    -0.46
    ‍♂️
    -0.43
     noires
    -0.43
     disparu
    -0.42
     huiles
    -0.42
     disfraces
    -0.42
     estação
    -0.42
    ----</
    -0.41
    POSITIVE LOGITS
     Roskov
    0.79
    UnsafeEnabled
    0.68
    NameInMap
    0.63
    TagMode
    0.59
     extracellular
    0.58
    ANEOUS
    0.56
     Integrity
    0.56
     physiology
    0.55
     urethra
    0.55
     Tract
    0.55
    Activations Density 0.043%

    No Known Activations