© 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. 0-CLT-HP
    7. 94357
    Prev
    Next
    INDEX
    Explanations

    cuticle

    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
     Toward
    -0.66
     Bigelow
    -0.58
     cuticle
    -0.55
    HomeAsUpEnabled
    -0.54
     Henri
    -0.53
    asticity
    -0.52
    gdx
    -0.51
    invokeLater
    -0.51
     متعلقه
    -0.51
    iesis
    -0.50
    POSITIVE LOGITS
    }\]
    0.62
    》.
    0.57
     setPassword
    0.57
     propOrder
    0.55
     ISTAT
    0.54
    '),
    0.52
     PrintWriter
    0.50
    "]]
    0.50
     yyj
    0.50
    OGND
    0.50
    Activations Density 1.327%

    No Known Activations