© 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. 92964
    Prev
    Next
    INDEX
    Explanations

    Code/Documentation snippets

    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
     nét
    -0.51
    ]='\
    -0.50
     Matéri
    -0.47
     Hardware
    -0.45
    </tr>
    -0.45
    Layout
    -0.45
    ọt
    -0.45
    ikus
    -0.45
    ikan
    -0.45
    ays
    -0.44
    POSITIVE LOGITS
    ReusableCell
    0.78
     is
    0.77
     مشين
    0.75
    MLLoader
    0.70
     snippetHide
    0.69
     AssemblyCulture
    0.68
     everyone
    0.68
     do
    0.65
    zzleHttp
    0.65
     autorytatywna
    0.63
    Activations Density 0.000%

    No Known Activations