© 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. 42337
    Prev
    Next
    INDEX
    Explanations

    Customization/Las Vegas

    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
    tail
    -0.75
     tailored
    -0.70
     customized
    -0.68
     las
    -0.65
    Tail
    -0.63
    e
    -0.57
     tailor
    -0.56
     customised
    -0.55
     Tan
    -0.54
     Tail
    -0.54
    POSITIVE LOGITS
    ]")]
    0.82
     '\\;'
    0.81
     noDo
    0.78
     وتسجيلات
    0.70
     فريبيس
    0.68
    lapsingToolbar
    0.66
    contentLoaded
    0.64
    AndEndTag
    0.64
     invokingState
    0.64
    paravant
    0.63
    Activations Density 0.233%

    No Known Activations