© 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. 93065
    Prev
    Next
    INDEX
    Explanations

    artment

    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
     diversify
    -0.66
    zzleHttp
    -0.66
    titleMargin
    -0.59
     Se
    -0.58
     Sa
    -0.55
    artment
    -0.54
     виправивши
    -0.54
    phus
    -0.52
     configureStore
    -0.51
     FID
    -0.48
    POSITIVE LOGITS
     ſtill
    0.59
     Jefus
    0.59
     særlig
    0.58
     raiſ
    0.57
     becauſe
    0.57
     doubtnut
    0.57
     faſt
    0.56
    felves
    0.54
    Portail
    0.54
     itſelf
    0.53
    Activations Density 0.116%

    No Known Activations