© 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. 42997
    Prev
    Next
    INDEX
    Explanations

    unlawful

    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
    AnchorStyles
    -0.75
    UserScript
    -0.73
    tvguidetime
    -0.68
    WebVitals
    -0.67
    IndentedString
    -0.65
    hoeddwyd
    -0.63
    arXiv
    -0.61
    findpost
    -0.60
    (!__
    -0.59
     CreateTagHelper
    -0.57
    POSITIVE LOGITS
    Geplaatst
    0.71
    ISTICS
    0.53
    IZING
    0.52
    ising
    0.52
    isation
    0.51
    ulation
    0.50
    ULATION
    0.50
    irs
    0.50
    OGND
    0.50
    s
    0.50
    Activations Density 0.576%

    No Known Activations