© 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. 20-CLT-HP
    7. 72142
    Prev
    Next
    INDEX
    Explanations

    Skill level

    np_max-act-logits · 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
     behind
    -1.33
    behind
    -1.27
     Behind
    -1.20
    Behind
    -1.15
     derrière
    -1.12
     BEHIND
    -1.11
     detrás
    -1.04
     dietro
    -1.01
    after
    -0.95
     atrás
    -0.94
    POSITIVE LOGITS
     intermediate
    0.61
     upper
    0.56
     INTER
    0.53
     Inter
    0.50
     lower
    0.50
     intermedi
    0.49
     intermediates
    0.49
     gev
    0.49
    rrggbb
    0.47
     experienced
    0.46
    Activations Density 0.000%

    No Known Activations