© 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. 0-CLT-HP
    7. 43344
    Prev
    Next
    INDEX
    Explanations

    commonly

    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
    ChildScrollView
    -0.77
     commonly
    -0.75
     ब्रेकडाउन
    -0.72
    </tfoot>
    -0.71
     Often
    -0.70
     frequently
    -0.69
     }</
    -0.67
     doInBackground
    -0.67
    commonly
    -0.67
    IndentedString
    -0.67
    POSITIVE LOGITS
    MigrationBuilder
    0.49
     crossing
    0.48
    ising
    0.42
    izing
    0.41
    itas
    0.41
    sey
    0.41
     surpassing
    0.41
     ['$
    0.40
     and
    0.40
     infected
    0.40
    Activations Density 0.049%

    No Known Activations