© 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. 9122
    Prev
    Next
    INDEX
    Explanations

    Nagoya

    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
    -1.16
    mog
    -1.16
     GenerationType
    -0.79
    rungsseite
    -0.77
     Савезне
    -0.76
    findpost
    -0.75
    EndGlobalSection
    -0.72
    tagHelperRunner
    -0.72
    basicConfig
    -0.69
    ImageContext
    -0.66
    POSITIVE LOGITS
    TT
    0.48
     blanda
    0.44
    ting
    0.44
    s
    0.44
     mâ
    0.44
    for
    0.43
    scan
    0.43
     acet
    0.43
    (
    0.42
     cabin
    0.42
    Activations Density 0.033%

    No Known Activations