© 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. 961
    Prev
    Next
    INDEX
    Explanations

    in

    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
     Signalez
    -0.83
     متعلقه
    -0.79
    providedIn
    -0.69
    المكان
    -0.68
     présidenti
    -0.66
     itſelf
    -0.63
     onPostExecute
    -0.60
     rése
    -0.60
     Rptr
    -0.60
    Activity
    -0.59
    POSITIVE LOGITS
    findpost
    0.48
     leg
    0.47
    avares
    0.44
    logy
    0.43
    annin
    0.42
    utebol
    0.41
    __))
    0.41
     المعيارى
    0.41
    :
    0.40
     z
    0.39
    Activations Density 0.005%

    No Known Activations