© 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. 92110
    Prev
    Next
    INDEX
    Explanations

    web search snippets

    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
    XmlAccessType
    -0.89
     referenties
    -0.87
     createSprite
    -0.81
    WithIOException
    -0.78
     NSCoder
    -0.73
     Signalez
    -0.73
    StoryboardSegue
    -0.72
    ();)
    -0.72
    DockStyle
    -0.71
    colgroup
    -0.68
    POSITIVE LOGITS
     to
    0.56
     allowing
    0.46
     allows
    0.43
    ?
    0.43
    cesa
    0.43
    enumi
    0.43
     allow
    0.40
     but
    0.39
    Über
    0.39
     mou
    0.38
    Activations Density 0.018%

    No Known Activations