© 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. 94133
    Prev
    Next
    INDEX
    Explanations

    Analysis/Reporting

    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
    __":
    -0.67
    ChildScrollView
    -0.59
    </tfoot>
    -0.57
    __':
    -0.56
     CommonModule
    -0.55
    PhysRevD
    -0.55
     Signalez
    -0.54
    __':
    -0.54
    قایناق‌لار
    -0.54
    الدراسه
    -0.53
    POSITIVE LOGITS
    libft
    0.50
     հղումներ
    0.50
    AndEndTag
    0.49
     RESERVED
    0.48
    quiries
    0.48
     Biôgrafia
    0.47
     noy
    0.46
    本日は
    0.44
    key
    0.43
    nosi
    0.43
    Activations Density 0.003%

    No Known Activations