© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 842
    Prev
    Next
    INDEX
    Explanations

    Isolation and separation

    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
    ://$
    -0.68
    BeginContext
    -0.55
    órum
    -0.54
    rophoto
    -0.53
    getChildAt
    -0.52
    guero
    -0.52
    HttpFoundation
    -0.50
    erval
    -0.50
    OSSARY
    -0.50
     cop
    -0.50
    POSITIVE LOGITS
     lenker
    0.63
     yourselves
    0.59
     незавершена
    0.59
     BorderRadius
    0.56
     ourselves
    0.56
    GEBURTSDATUM
    0.56
     awakeFromNib
    0.55
    Stayed
    0.53
    OGND
    0.52
    AndEndTag
    0.50
    Activations Density 0.000%

    No Known Activations