© 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. 92315
    Prev
    Next
    INDEX
    Explanations

    harmful substances

    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
    <bos>
    -0.72
    OGND
    -0.66
    oogle
    -0.52
    sidemargin
    -0.51
    ChildScrollView
    -0.51
     calendriers
    -0.51
    ctrica
    -0.50
    Rè
    -0.49
    Begriffsklä
    -0.48
     الرياضيه
    -0.48
    POSITIVE LOGITS
     Audiodateien
    0.64
     OnTriggerEnter
    0.62
     Waray
    0.58
     >=",
    0.57
     Injuries
    0.53
    byes
    0.52
    miller
    0.52
     faim
    0.51
     <=",
    0.50
     arşivlendi
    0.49
    Activations Density 0.000%

    No Known Activations