© 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. 5-CLT-HP
    7. 5190
    Prev
    Next
    INDEX
    Explanations

    roles

    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
    isEmail
    -0.40
    LEEP
    -0.38
     legislator
    -0.37
    ISSE
    -0.36
    uria
    -0.35
     zewnętrzne
    -0.34
    tagext
    -0.34
     hini
    -0.34
     pré
    -0.33
     Moe
    -0.33
    POSITIVE LOGITS
    SequentialGroup
    0.88
    UrlResolution
    0.80
     girls
    0.80
     girl
    0.79
    ConstraintMaker
    0.78
    girl
    0.76
    writerow
    0.75
    AsUp
    0.75
     kasarigan
    0.71
    girls
    0.71
    Activations Density 0.001%

    No Known Activations