© 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. 4-CLT-HP
    7. 990
    Prev
    Next
    INDEX
    Explanations

    creation and production

    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
     Placing
    -0.72
     Storing
    -0.70
    Are
    -0.69
     ?>>
    -0.65
    utilisons
    -0.64
     SETTING
    -0.63
    Portail
    -0.63
    are
    -0.63
    have
    -0.61
     Telling
    -0.61
    POSITIVE LOGITS
     is
    0.66
     has
    0.55
     was
    0.52
     continues
    0.45
    NOPQRST
    0.45
     hasn
    0.45
    олові
    0.44
     occurs
    0.44
     by
    0.42
     wasn
    0.42
    Activations Density 0.002%

    No Known Activations