© 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. 15011
    Prev
    Next
    INDEX
    Explanations

    fishing

    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
     Walkover
    -0.52
     keter
    -0.49
    PullParser
    -0.48
     للاسماء
    -0.47
     plan
    -0.45
     Marina
    -0.44
    зит
    -0.44
     par
    -0.44
     rec
    -0.43
     Marsh
    -0.43
    POSITIVE LOGITS
     myſelf
    0.68
    iedenis
    0.65
     itſelf
    0.63
    ritsar
    0.63
    MessageTagHelper
    0.62
    NamedQueries
    0.60
     ſche
    0.59
    __*/
    0.59
    IntoConstraints
    0.59
    Datuak
    0.58
    Activations Density 0.102%

    No Known Activations