© 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. 20-CLT-HP
    7. 75348
    Prev
    Next
    INDEX
    Explanations

    single digits

    np_max-act-logits · 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
    uxxxx
    -0.55
     onCancelled
    -0.47
    ativement
    -0.45
     Quis
    -0.44
    ranean
    -0.41
     calendriers
    -0.41
     commanded
    -0.41
     intervening
    -0.40
     retiring
    -0.40
    bzero
    -0.40
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.71
     Wikimedijinoj
    0.70
    IVEREF
    0.68
    IUrlHelper
    0.68
    Enllaços
    0.68
    XmlAccessType
    0.65
    homonymie
    0.65
     estekak
    0.63
    ècie
    0.63
    Manbalar
    0.63
    Activations Density 0.123%

    No Known Activations