© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91104
    Prev
    Next
    INDEX
    Explanations

    code

    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
    Negative Logits
     pinulongan
    -0.76
     anyone
    -0.75
     any
    -0.74
     Signalez
    -0.71
    argout
    -0.70
     resourceCulture
    -0.68
     ddelweddau
    -0.65
     MotionEvent
    -0.65
    msgTypes
    -0.64
     anything
    -0.63
    POSITIVE LOGITS
    раздо
    0.57
    FontOfSize
    0.56
     mourut
    0.54
     fapt
    0.53
    cektir
    0.53
     sahiptir
    0.53
     Uncertainty
    0.50
     Identity
    0.49
     Aggression
    0.49
     merveilleux
    0.48
    Activations Density 0.055%

    No Known Activations