© 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. 0-CLT-HP
    7. 42390
    Prev
    Next
    INDEX
    Explanations

    documentation/technical contexts

    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
    -0.84
    abestanden
    -0.73
    Turns
    -0.71
     Statement
    -0.68
     STATEMENT
    -0.64
     disambiguazione
    -0.64
     ujednoznacz
    -0.61
    resizingMask
    -0.61
    Statement
    -0.60
    出版年
    -0.60
    POSITIVE LOGITS
     MonoBehaviour
    0.62
    ])));
    0.52
     Cow
    0.52
    cyjna
    0.51
    eral
    0.51
     Row
    0.50
     Hor
    0.49
    cjach
    0.49
     Film
    0.48
    oon
    0.48
    Activations Density 0.196%

    No Known Activations