© 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. 15248
    Prev
    Next
    INDEX
    Explanations

    of

    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
    िखित
    -0.51
    igsaw
    -0.48
    OfBirth
    -0.48
     Konkur
    -0.47
    ouvoir
    -0.47
    THEW
    -0.47
     retribution
    -0.46
     neglect
    -0.46
    })->
    -0.46
    ôle
    -0.45
    POSITIVE LOGITS
    RegressionTest
    0.67
    abestanden
    0.67
     متعلقه
    0.66
    oredCriteria
    0.65
    GraphicsUnit
    0.64
     protoimpl
    0.64
    исленность
    0.63
     propOrder
    0.63
    GEBURTSDATUM
    0.62
     the
    0.60
    Activations Density 0.026%

    No Known Activations