© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92774
    Prev
    Next
    INDEX
    Explanations

    inund

    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
    tvguidetime
    -0.57
     المعيارى
    -0.53
     inund
    -0.49
     honor
    -0.48
     extend
    -0.48
    Neighbors
    -0.48
     ITIS
    -0.48
     abundance
    -0.47
    힘
    -0.43
     wind
    -0.43
    POSITIVE LOGITS
    NameInMap
    0.93
     defaultstate
    0.84
     Normdatei
    0.76
    ⓧ
    0.73
     kasarigan
    0.72
     **/
    0.71
    angliski
    0.71
    Hentet
    0.70
    PMailer
    0.68
    NewUrlParser
    0.67
    Activations Density 0.239%

    No Known Activations