© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92952
    Prev
    Next
    INDEX
    Explanations

    solving

    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
    Tikang
    -0.75
    RTEE
    -0.68
    دانشنامهٔ
    -0.64
     Audiodateien
    -0.62
     laikā
    -0.62
     protoimpl
    -0.61
     propOrder
    -0.59
     decreto
    -0.59
    GMENT
    -0.58
    tilhe
    -0.57
    POSITIVE LOGITS
     disputes
    0.87
     claims
    0.71
     questions
    0.66
     complaints
    0.66
     controversies
    0.65
     Disputes
    0.64
     issues
    0.62
     all
    0.62
     disputed
    0.59
     concerns
    0.57
    Activations Density 0.001%

    No Known Activations