© 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. 5-CLT-HP
    7. 4762
    Prev
    Next
    INDEX
    Explanations

    Grammar/sentence structure

    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
    <bos>
    -0.63
     troup
    -0.51
    nasse
    -0.50
    unicaciones
    -0.48
     Beschäf
    -0.47
    담
    -0.47
     RET
    -0.47
    HtmlAttribute
    -0.46
    onet
    -0.46
    acias
    -0.46
    POSITIVE LOGITS
    Παραπομπές
    0.68
    expandindo
    0.67
    BufferException
    0.66
    ResumeLayout
    0.65
    ValueStyle
    0.64
    LLocation
    0.63
    Portail
    0.62
    InstrumentedTest
    0.62
    CppMethod
    0.61
    zzleHttp
    0.60
    Activations Density 0.003%

    No Known Activations