© 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. 43100
    Prev
    Next
    INDEX
    Explanations

    role

    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
     role
    -1.52
    role
    -1.21
     itſelf
    -1.14
     Efq
    -1.10
     Role
    -1.08
     purpoſe
    -1.06
     myſelf
    -1.06
    neſs
    -1.05
     houſe
    -1.02
     ſtate
    -1.02
    POSITIVE LOGITS
     in
    0.98
    in
    0.67
     of
    0.59
    :
    0.59
    !
    0.59
    .
    0.59
    ;
    0.57
     
    0.55
    (
    0.54
     on
    0.53
    Activations Density 0.058%

    No Known Activations