© 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. 91405
    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
     region
    -0.61
     local
    -0.57
     living
    -0.53
     residents
    -0.51
    Residents
    -0.51
     regional
    -0.49
     inhabitants
    -0.48
    Locals
    -0.47
    region
    -0.44
     noqa
    -0.44
    POSITIVE LOGITS
    expandindo
    1.00
    Enllaces
    0.81
    SourceChecksum
    0.77
    AnchorStyles
    0.67
     autorytatywna
    0.66
     виправивши
    0.66
    RenderAtEndOf
    0.66
     AssemblyTitle
    0.65
     theſe
    0.64
     thefe
    0.63
    Activations Density 0.000%

    No Known Activations