© 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. 14755
    Prev
    Next
    INDEX
    Explanations

    seemingly random words

    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
    zin
    -0.97
    HM
    -0.94
     Herr
    -0.88
     HM
    -0.87
    Herr
    -0.68
    ZIN
    -0.67
     TextInputType
    -0.64
    StructEnd
    -0.60
     yawning
    -0.60
    Tween
    -0.59
    POSITIVE LOGITS
    GOTREF
    0.49
     DOH
    0.48
    ero
    0.46
    ⓧ
    0.42
    ers
    0.42
    eras
    0.42
     hot
    0.40
     Hot
    0.40
    hot
    0.39
    actéristique
    0.39
    Activations Density 0.035%

    No Known Activations