© 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. 93737
    Prev
    Next
    INDEX
    Explanations

    Informal 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
     somehow
    -1.31
     Somehow
    -1.30
    Somehow
    -1.23
     irgendwie
    -0.91
     Somewhere
    -0.79
     miraculously
    -0.72
    StoreMessageInfo
    -0.71
     somewhere
    -0.70
    脚注の使い方
    -0.69
     Anſ
    -0.69
    POSITIVE LOGITS
     respectively
    0.50
    numerusform
    0.50
    ("")]
    0.49
    }`}
    0.48
    TemporalType
    0.48
    <bos>
    0.47
     vero
    0.45
    可不
    0.45
    jena
    0.44
    typeorm
    0.44
    Activations Density 0.031%

    No Known Activations