© 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. 43426
    Prev
    Next
    INDEX
    Explanations

    CB

    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
    RB
    -0.73
    SB
    -0.63
    o
    -0.60
    CB
    -0.57
    LB
    -0.52
     CB
    -0.52
     AB
    -0.52
    EB
    -0.51
     •
    -0.48
    AAT
    -0.46
    POSITIVE LOGITS
     Efq
    1.47
     myſelf
    1.34
     itſelf
    1.24
    ſelves
    1.23
     raiſ
    1.22
     Majefty
    1.21
     pleaſure
    1.16
     Jefus
    1.16
     Anſ
    1.13
     Diſ
    1.12
    Activations Density 0.641%

    No Known Activations