© 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. 14384
    Prev
    Next
    INDEX
    Explanations

    {}

    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
     GENERATED
    -0.55
    Demografía
    -0.53
    uldron
    -0.49
    salms
    -0.47
    ObjectMeta
    -0.47
     AssemblyCompany
    -0.47
    cibles
    -0.46
    orology
    -0.46
    stdc
    -0.45
    ัติ
    -0.45
    POSITIVE LOGITS
    NOPQRST
    0.70
    GOTREF
    0.68
     المعيارى
    0.65
    findpost
    0.63
    +#+#
    0.59
    CloseOperation
    0.59
    GraphicsUnit
    0.59
    reactstrap
    0.58
    qtype
    0.55
    Pyx
    0.54
    Activations Density 0.242%

    No Known Activations