© 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. 5-CLT-HP
    7. 92542
    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
    dresser
    -0.65
     سكانية
    -0.60
    juries
    -0.59
     JpaRepository
    -0.56
    Personensuche
    -0.56
    GenerationType
    -0.55
    BorderLayout
    -0.54
     endforeach
    -0.54
     CURIAM
    -0.54
    verwijspagina
    -0.54
    POSITIVE LOGITS
     how
    0.72
     who
    0.69
     ourselves
    0.69
     us
    0.68
     our
    0.62
    who
    0.61
     yourself
    0.54
     transfieras
    0.53
     what
    0.52
    paž
    0.51
    Activations Density 0.000%

    No Known Activations