© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3045
    Prev
    Next
    INDEX
    Explanations

    Malformed/fragmented text

    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
     CanadaChoose
    -0.64
    <bos>
    -0.63
    schild
    -0.62
    +#+
    -0.62
     useHistory
    -0.58
     AssemblyTitle
    -0.57
     Inscrivez
    -0.57
    Aholisi
    -0.54
    expandindo
    -0.54
    prepareStatement
    -0.51
    POSITIVE LOGITS
     Vikipedi
    0.52
    uría
    0.49
     communiquer
    0.46
    ByVersion
    0.44
     lunettes
    0.44
     consultar
    0.44
     mouseY
    0.44
     Beratung
    0.43
     sacerd
    0.43
    قایناقلار
    0.42
    Activations Density 0.000%

    No Known Activations