© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38702
    Prev
    Next
    INDEX
    Explanations

    EndProject

    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
    logrus
    -0.50
    PerPage
    -0.48
     mere
    -0.47
     pháp
    -0.47
     ấn
    -0.45
     useStyles
    -0.44
     golfe
    -0.43
    kamen
    -0.43
    ?></
    -0.43
    avar
    -0.43
    POSITIVE LOGITS
    MLLoader
    1.00
     ISNI
    0.84
    ఔ
    0.82
     Reverso
    0.78
     ProtoMessage
    0.78
    twimg
    0.75
    ⓧ
    0.74
    OGND
    0.73
     NUKAT
    0.73
     surla
    0.73
    Activations Density 0.029%

    No Known Activations