© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 98150
    Prev
    Next
    INDEX
    Explanations

    scientific writing

    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
    SequentialGroup
    -0.90
    TestingModule
    -0.76
    kloped
    -0.71
    obium
    -0.69
    Rhestr
    -0.69
     Houſe
    -0.68
    NgModule
    -0.68
     itſelf
    -0.68
     Estelle
    -0.66
     Etrus
    -0.66
    POSITIVE LOGITS
     and
    0.64
    )))));
    0.54
    writeFieldEnd
    0.50
    帖最后由
    0.49
    :✨
    0.45
     amelyek
    0.43
    ,
    0.41
    )];
    
    0.40
    的同时
    0.38
    ))));
    0.37
    Activations Density 0.000%

    No Known Activations