© 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. 20-CLT-HP
    7. 71845
    Prev
    Next
    INDEX
    Explanations

    scientific publications

    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
    DockStyle
    -0.58
     Louvain
    -0.51
     ISTAT
    -0.50
    醐
    -0.47
    SetId
    -0.46
    MigrationBuilder
    -0.45
    #+#
    -0.44
    )__
    -0.43
     Чита
    -0.43
    getParams
    -0.43
    POSITIVE LOGITS
    CloseOperation
    0.64
    twimg
    0.63
    ExtendWith
    0.62
     Ress
    0.54
    webElementXpaths
    0.52
     Normdatei
    0.52
    uses
    0.52
    ufe
    0.50
    ink
    0.50
    using
    0.49
    Activations Density 0.000%

    No Known Activations