© 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. 5-CLT-HP
    7. 91922
    Prev
    Next
    INDEX
    Explanations

    That

    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
    ürtel
    -0.44
    لار
    -0.41
    IonicModule
    -0.41
    arques
    -0.40
    thun
    -0.40
     deepcopy
    -0.39
    adhi
    -0.38
    ばかり
    -0.38
    Commons
    -0.37
    pong
    -0.37
    POSITIVE LOGITS
     disambiguazione
    0.82
    تقاوى
    0.71
    ViewImports
    0.68
    :
    0.68
     pinulongan
    0.67
     calendriers
    0.66
    styleType
    0.66
    AnchorStyles
    0.65
    SourceChecksum
    0.64
     EconPapers
    0.63
    Activations Density 0.001%

    No Known Activations