© 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. 10144
    Prev
    Next
    INDEX
    Explanations

    stationery

    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
    ghijklmnop
    -0.62
     AMC
    -0.61
    AMC
    -0.57
    StoreMessageInfo
    -0.54
    rmızı
    -0.53
     scolaires
    -0.51
    drawiam
    -0.50
     punte
    -0.50
     kasarigan
    -0.50
     pesado
    -0.50
    POSITIVE LOGITS
    s
    0.88
    sv
    0.65
    DockStyle
    0.62
    ########.
    0.60
    shi
    0.58
     cherchés
    0.57
    sy
    0.55
    nocache
    0.54
    ski
    0.52
    ⓧ
    0.52
    Activations Density 0.011%

    No Known Activations