© 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. 0-CLT-HP
    7. 42874
    Prev
    Next
    INDEX
    Explanations

    directions and movement

    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
     supplémentaires
    -0.69
     alimentaires
    -0.65
     preocupes
    -0.64
    <tfoot>
    -0.59
     entanto
    -0.58
    midler
    -0.56
     merve
    -0.55
     responseData
    -0.55
    zwischen
    -0.53
     supplémentaire
    -0.53
    POSITIVE LOGITS
     the
    0.74
     iprot
    0.59
    mtrl
    0.58
    OGND
    0.57
    essoas
    0.57
     what
    0.56
     our
    0.54
     future
    0.54
     person
    0.53
     people
    0.51
    Activations Density 0.177%

    No Known Activations