© 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. 15843
    Prev
    Next
    INDEX
    Explanations

    four

    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
    UnknownFields
    -0.66
    thâu
    -0.61
     Bluestacks
    -0.58
    uxxxx
    -0.57
    GraphicsUnit
    -0.57
    kháu
    -0.53
    UnsafeEnabled
    -0.52
    lammatory
    -0.52
    <bos>
    -0.52
    Gweler
    -0.51
    POSITIVE LOGITS
    tagHelperRunner
    0.58
    esModule
    0.57
     Sén
    0.54
    لينكات
    0.47
     addSubview
    0.45
    EndContext
    0.44
    _()
    0.44
    )))));
    0.44
     transfieras
    0.43
     "\""
    0.43
    Activations Density 0.095%

    No Known Activations