© 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. 14357
    Prev
    Next
    INDEX
    Explanations

    to

    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
     propOrder
    -0.68
     estimés
    -0.67
    ագրություններ
    -0.65
    లాలు
    -0.64
     ModelExpression
    -0.62
     lèvres
    -0.61
     antemano
    -0.60
    jalá
    -0.60
     cremallera
    -0.58
     antaranya
    -0.58
    POSITIVE LOGITS
     the
    1.28
     a
    0.77
     an
    0.74
     clarification
    0.73
     its
    0.72
     converting
    0.71
     their
    0.71
     improving
    0.71
     warming
    0.69
     detecting
    0.69
    Activations Density 0.022%

    No Known Activations