© 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. 9935
    Prev
    Next
    INDEX
    Explanations

    x

    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
     déchir
    -0.52
    marginHorizontal
    -0.51
    marginVertical
    -0.51
     idéia
    -0.46
    cerpts
    -0.45
     océano
    -0.45
    marin
    -0.43
     lèvres
    -0.43
     voluntarios
    -0.43
     než
    -0.43
    POSITIVE LOGITS
    ftagPool
    0.90
     esternos
    0.64
     متعلقه
    0.64
     كومونز
    0.63
    writeField
    0.62
    pexpr
    0.62
    webElement
    0.61
    complexType
    0.60
    bootstrapcdn
    0.58
    Personendaten
    0.58
    Activations Density 0.141%

    No Known Activations