© 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. 5-CLT-HP
    7. 92637
    Prev
    Next
    INDEX
    Explanations

    increase

    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
    fromnode
    -0.61
     astore
    -0.58
    Portail
    -0.56
     Whence
    -0.54
    ABOVE
    -0.54
    rotnie
    -0.53
    <?>>
    -0.52
     poffe
    -0.51
     MainAxisSize
    -0.51
     itſelf
    -0.50
    POSITIVE LOGITS
     we
    0.63
     seen
    0.56
     for
    0.55
     recorded
    0.54
    TabIndex
    0.52
     registrados
    0.50
     with
    0.48
     révélé
    0.47
    BeginContext
    0.46
     tallied
    0.46
    Activations Density 0.003%

    No Known Activations