© 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. 14867
    Prev
    Next
    INDEX
    Explanations

    web addresses and titles

    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
     lak
    -0.52
    land
    -0.47
    ا
    -0.46
    tedly
    -0.45
    lands
    -0.45
    isome
    -0.44
    lii
    -0.43
    odle
    -0.43
    a
    -0.43
    rous
    -0.42
    POSITIVE LOGITS
    (!__
    0.74
     arşivlendi
    0.72
    DotNetBar
    0.71
    RectangleBorder
    0.70
    Portail
    0.66
     المعيارى
    0.64
    󠁢
    0.63
    providedIn
    0.62
     صوتيه
    0.61
    IVEREF
    0.59
    Activations Density 0.018%

    No Known Activations