© 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. 5-CLT-HP
    7. 91788
    Prev
    Next
    INDEX
    Explanations

    comparisons, exceeding

    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
    ProcessEvent
    -0.55
     remarqué
    -0.53
    SOUNDBITE
    -0.52
     dům
    -0.51
    WindowEvent
    -0.49
     pouvoirs
    -0.49
     residentes
    -0.48
     undangan
    -0.47
     espirituales
    -0.46
    Sentry
    -0.46
    POSITIVE LOGITS
    +#+#
    0.65
     Stere
    0.61
     mergeFrom
    0.59
     itſelf
    0.58
     Surface
    0.58
    帖最后由
    0.56
    =?";
    0.56
     Labels
    0.56
    Labels
    0.54
     Bibli
    0.54
    Activations Density 0.002%

    No Known Activations