© 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. 42854
    Prev
    Next
    INDEX
    Explanations

    Structural markup/notation

    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
    ↵
    -1.59
    ↵↵
    -1.59
     
    -1.33
    ,
    -1.23
    '
    -1.20
    ’
    -1.17
     to
    -1.16
    <bos>
    -1.14
    -
    -1.14
     and
    -1.13
    POSITIVE LOGITS
     Efq
    2.38
     itſelf
    2.25
     myſelf
    2.20
     iſt
    2.19
     ―――――
    2.13
     Jefus
    2.06
     ſeveral
    2.06
    ſelf
    2.03
    ^(@)
    2.03
     doubtnut
    2.02
    Activations Density 0.020%

    No Known Activations