© 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. 93850
    Prev
    Next
    INDEX
    Explanations

    awards

    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
    certified
    -0.68
    Certified
    -0.64
     certified
    -0.58
    atics
    -0.56
    arschu
    -0.55
    CERT
    -0.55
     nahilalakip
    -0.54
    Portale
    -0.53
     calibrated
    -0.53
    MenuGroup
    -0.53
    POSITIVE LOGITS
     podjela
    0.59
     bris
    0.57
    iempos
    0.56
    ptos
    0.55
     виправивши
    0.55
    InSection
    0.55
    rophes
    0.53
    LikeLike
    0.53
    الإنجليزية
    0.53
     defenses
    0.52
    Activations Density 0.061%

    No Known Activations