© 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. 92778
    Prev
    Next
    INDEX
    Explanations

    may

    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
    InjectAttribute
    -0.68
     resourceCulture
    -0.66
    TestingModule
    -0.65
    featureID
    -0.63
     ApiException
    -0.62
    StructEnd
    -0.58
    parsedMessage
    -0.58
    AnimationsModule
    -0.57
     MenuView
    -0.56
    Parcelize
    -0.56
    POSITIVE LOGITS
     tell
    0.57
     poema
    0.56
     told
    0.54
    Told
    0.54
     telling
    0.53
    новниш
    0.53
     myth
    0.52
     conversations
    0.51
     programme
    0.51
     songs
    0.50
    Activations Density 0.002%

    No Known Activations