© 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. 1-CLT-HP
    7. 9808
    Prev
    Next
    INDEX
    Explanations

    insects

    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
     espirituales
    -0.68
     समीक्षक
    -0.65
     colorés
    -0.63
     détru
    -0.63
     africains
    -0.62
    ftagPool
    -0.61
     blessés
    -0.61
     médié
    -0.61
     jorden
    -0.60
     murieron
    -0.60
    POSITIVE LOGITS
    ational
    0.53
     officers
    0.53
     agent
    0.52
     pest
    0.50
     agents
    0.50
    bolista
    0.50
     illumin
    0.49
    PreferredItem
    0.49
    RenderAtEndOf
    0.48
    ury
    0.48
    Activations Density 0.030%

    No Known Activations