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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 39869
    Prev
    Next
    INDEX
    Explanations

    research studies

    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
    <eos>
    -0.72
     Following
    -0.70
     Many
    -0.68
     Unlike
    -0.67
     Whatever
    -0.67
     Often
    -0.65
    Whatever
    -0.65
    Contrary
    -0.65
    c
    -0.65
    .
    -0.65
    POSITIVE LOGITS
     ―――――
    1.25
    ^(@)
    1.18
     $_"
    1.18
     itſelf
    1.14
     myſelf
    1.14
     purpoſe
    1.13
     Jefus
    1.10
     Efq
    1.09
     Majefty
    1.07
     ſeveral
    1.06
    Activations Density 0.180%

    No Known Activations