© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3676
    Prev
    Next
    INDEX
    Explanations

    machines and devices

    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
    XmlAccessType
    -0.56
    withIdentifier
    -0.53
    GIVEREF
    -0.53
    Mode
    -0.53
    fibra
    -0.49
    EnumType
    -0.49
     Mode
    -0.49
     vehicles
    -0.49
    iastes
    -0.49
     useRouter
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.61
     overboard
    0.57
    LookAnd
    0.57
    verwijspagina
    0.52
     ſeveral
    0.51
     outwards
    0.49
    @[+][
    0.48
     indoors
    0.48
     Slough
    0.48
     unde
    0.47
    Activations Density 0.005%

    No Known Activations