© 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. 20-CLT-HP
    7. 76988
    Prev
    Next
    INDEX
    Explanations

    scientific papers/code

    np_max-act-logits · 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
     חיצוניים
    -0.69
    Spoljašnje
    -0.61
     nakalista
    -0.56
    ask
    -0.55
    strijd
    -0.54
     protoimpl
    -0.53
    AllAfrica
    -0.53
    Aiheesta
    -0.53
    Referències
    -0.52
     bacio
    -0.52
    POSITIVE LOGITS
    ंदीखरीदारी
    0.53
    CollectionUtils
    0.49
     wach
    0.48
    KURZBESCHREIBUNG
    0.47
     doInBackground
    0.47
    insee
    0.46
    awaiter
    0.44
    wohl
    0.44
     right
    0.44
    ftagPool
    0.44
    Activations Density 0.010%

    No Known Activations