© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92911
    Prev
    Next
    INDEX
    Explanations

    End of sections

    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
     therefore
    -0.64
     generally
    -0.61
     or
    -0.58
     Público
    -0.57
     thereby
    -0.57
     secondly
    -0.57
     therefor
    -0.56
     bridesmaids
    -0.55
     leading
    -0.54
     commonly
    -0.54
    POSITIVE LOGITS
     fermés
    0.69
     boî
    0.65
    MigrationBuilder
    0.63
    MessageOf
    0.59
     lèvres
    0.58
     vaisseaux
    0.57
     étan
    0.57
    +#+#
    0.57
    <bos>
    0.55
     pertes
    0.52
    Activations Density 0.000%

    No Known Activations