© 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. 42579
    Prev
    Next
    INDEX
    Explanations

    scoring

    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
     score
    -1.46
     scoring
    -1.27
    score
    -1.23
    scoring
    -1.19
     Scoring
    -1.12
    Scoring
    -1.11
     scored
    -1.10
     drive
    -1.05
    scored
    -1.03
     Score
    -0.98
    POSITIVE LOGITS
     meta
    0.58
     behavior
    0.51
     the
    0.49
    deel
    0.49
    overs
    0.49
     Meta
    0.49
     appendages
    0.48
     Whisper
    0.48
     general
    0.48
    Review
    0.47
    Activations Density 0.313%

    No Known Activations