© 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. 93919
    Prev
    Next
    INDEX
    Explanations

    no

    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
     approaches
    -0.74
     lemmas
    -0.66
     influences
    -0.64
     prijzen
    -0.63
     concentrates
    -0.61
     formats
    -0.61
     prevails
    -0.61
     démission
    -0.61
     mounts
    -0.60
     steigt
    -0.60
    POSITIVE LOGITS
     longer
    0.65
    yntaxException
    0.63
    исленность
    0.59
     way
    0.58
     better
    0.57
     question
    0.55
     ModelExpression
    0.54
     telling
    0.52
    تقاوى
    0.52
     denying
    0.52
    Activations Density 0.138%

    No Known Activations