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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1613
    Prev
    Next
    INDEX
    Explanations

    chopping

    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
     Trainer
    -0.57
    webElement
    -0.55
     Drill
    -0.54
    arag
    -0.51
    henswürdigkeiten
    -0.51
     Counselor
    -0.51
     Votes
    -0.50
    ména
    -0.49
     Racer
    -0.49
     Ages
    -0.49
    POSITIVE LOGITS
    ocracy
    0.71
    less
    0.68
    theless
    0.61
    RenderAtEndOf
    0.60
    ality
    0.59
    fully
    0.59
    ally
    0.58
    ability
    0.56
     zitate
    0.56
     Roskov
    0.56
    Activations Density 0.067%

    No Known Activations