© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1025
    Prev
    Next
    INDEX
    Explanations

    investigations and explorations

    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
    PerformLayout
    -0.70
    @[+][
    -0.57
     CURIAM
    -0.56
     Parcelable
    -0.52
    ագրություններ
    -0.51
    эффици
    -0.50
     <<<<<<<<<<<<<<
    -0.50
     firebaseConfig
    -0.49
    ">//
    -0.49
     HttpNotFound
    -0.48
    POSITIVE LOGITS
     our
    0.69
     the
    0.67
    OURCE
    0.61
     whether
    0.58
     identity
    0.57
    什么是
    0.57
     civilization
    0.57
     Segurança
    0.57
     nationality
    0.56
     issues
    0.56
    Activations Density 0.001%

    No Known Activations