© 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. 93964
    Prev
    Next
    INDEX
    Explanations

    legal texts

    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
    stdc
    -0.66
     botanist
    -0.65
    horse
    -0.65
     Sigism
    -0.64
     monks
    -0.63
     spéciales
    -0.63
    ecap
    -0.63
     chopsticks
    -0.62
     automatiques
    -0.61
     extérieures
    -0.61
    POSITIVE LOGITS
     GetEnumerator
    0.54
     CanadaChoose
    0.54
    AddTagHelper
    0.53
    はじめに
    0.52
    HasForeignKey
    0.52
     ""],
    0.50
     defStyleAttr
    0.50
    észetes
    0.50
    vantages
    0.49
     board
    0.49
    Activations Density 0.514%

    No Known Activations