© 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. 9064
    Prev
    Next
    INDEX
    Explanations

    feld

    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
    feld
    -1.78
    feldt
    -1.17
    felder
    -1.09
    fel
    -0.80
    felde
    -0.71
    felt
    -0.67
     Feld
    -0.63
    Feld
    -0.61
     feld
    -0.57
    elstein
    -0.55
    POSITIVE LOGITS
     doInBackground
    0.72
     سكانية
    0.71
     snippetHide
    0.69
    Sucesor
    0.68
    dymyr
    0.66
     Montagu
    0.65
     DOMINGO
    0.65
     Huguen
    0.65
    gonic
    0.63
    IntentFilter
    0.63
    Activations Density 0.012%

    No Known Activations