© 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. 5-CLT-HP
    7. 91757
    Prev
    Next
    INDEX
    Explanations

    speculation

    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
     propOrder
    -0.57
    EntityId
    -0.50
     الحره
    -0.49
    enment
    -0.48
     TOT
    -0.48
    }")
    -0.47
    )}+
    -0.47
    Certainly
    -0.47
    Rujuakan
    -0.47
     Certainly
    -0.47
    POSITIVE LOGITS
    DTD
    0.56
     publiés
    0.54
     uska
    0.53
    antMatchers
    0.53
    addCriterion
    0.52
    jaro
    0.52
    djangoproject
    0.52
    basicConfig
    0.52
     claimed
    0.50
     reclamation
    0.50
    Activations Density 0.033%

    No Known Activations