© 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. 4-CLT-HP
    7. 799
    Prev
    Next
    INDEX
    Explanations

    drugs

    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
    afficheront
    -0.79
    ंदीखरीदारी
    -0.79
    LookAnd
    -0.78
    protoimpl
    -0.76
    profen
    -0.76
    Rhestr
    -0.75
    MessageTagHelper
    -0.75
    aarrggbb
    -0.75
    AddTagHelper
    -0.74
    󠁴
    -0.73
    POSITIVE LOGITS
    ėse
    0.39
     leaky
    0.37
     onCreate
    0.36
    Ź
    0.36
    pele
    0.35
     sportivo
    0.35
     lep
    0.35
    onos
    0.35
    pos
    0.35
    /
    0.35
    Activations Density 0.002%

    No Known Activations