© 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. 1-CLT-HP
    7. 15517
    Prev
    Next
    INDEX
    Explanations

    hands/fingers

    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
    MethodManager
    -0.60
     transfieras
    -0.56
     EconPapers
    -0.52
     finger
    -0.46
     JAXBElement
    -0.41
     Finger
    -0.40
     pint
    -0.40
    >());
    -0.39
    onian
    -0.38
    enumi
    -0.38
    POSITIVE LOGITS
    etka
    0.63
    Демографія
    0.62
     GenerationType
    0.60
    ніципа
    0.59
    colades
    0.59
     gql
    0.58
    Kedua
    0.57
    ingtones
    0.56
    XmlAccessType
    0.55
    turnstile
    0.55
    Activations Density 0.155%

    No Known Activations