© 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. 14612
    Prev
    Next
    INDEX
    Explanations

    code

    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
    aterin
    -1.11
    UrlResolution
    -0.62
     fore
    -0.52
     propOrder
    -0.52
     dAtA
    -0.51
    */;
    -0.50
    μως
    -0.50
     HttpHeaders
    -0.49
     referenties
    -0.49
     Yaman
    -0.49
    POSITIVE LOGITS
     resourceCulture
    0.84
     autorytatywna
    0.66
     nahilalakip
    0.61
    odar
    0.57
    SerializeField
    0.56
    blad
    0.53
     EconPapers
    0.52
    elemField
    0.49
    BigNumber
    0.49
    kloped
    0.48
    Activations Density 0.021%

    No Known Activations