© 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. 0-CLT-HP
    7. 94099
    Prev
    Next
    INDEX
    Explanations

    case

    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
     true
    -0.52
     True
    -0.45
    CAPTION
    -0.44
    وانید
    -0.41
     verdaderos
    -0.40
    ']=='
    -0.39
     dessus
    -0.39
    ktır
    -0.38
     JAXBElement
    -0.38
     vraie
    -0.38
    POSITIVE LOGITS
    TestingModule
    0.76
     Infórmanos
    0.73
     nahilalakip
    0.71
     Roskov
    0.71
     referenties
    0.68
    simile
    0.66
     Савезне
    0.65
    PreExecute
    0.65
    esez
    0.63
    клопе
    0.61
    Activations Density 0.028%

    No Known Activations