© 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. 367
    Prev
    Next
    INDEX
    Explanations

    of

    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
    Personensuche
    -0.59
     ujednoznacz
    -0.49
    ViewFeatures
    -0.49
    providedIn
    -0.47
    </h4>
    -0.45
    存于互联网档案馆
    -0.44
    '''
    -0.44
     الحره
    -0.42
     Wikimedijinoj
    -0.42
    KommentareTeilen
    -0.41
    POSITIVE LOGITS
     the
    0.84
     mergeFrom
    0.63
    CloseOperation
    0.63
     proportional
    0.55
    UnknownFields
    0.54
    jectures
    0.54
    曖昧さ回避
    0.54
     fixed
    0.54
     The
    0.53
    EndContext
    0.53
    Activations Density 0.001%

    No Known Activations