© 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. 20-CLT-HP
    7. 77749
    Prev
    Next
    INDEX
    Explanations

    almost

    np_max-act-logits · 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
    rungsseite
    -1.04
    HasForeignKey
    -0.94
    脚注の使い方
    -0.93
     propOrder
    -0.88
    AndEndTag
    -0.85
    VIAF
    -0.84
    parsedMessage
    -0.82
    SharedCtor
    -0.80
    новниш
    -0.79
     AssemblyTitle
    -0.79
    POSITIVE LOGITS
     almost
    0.35
    <
    0.34
    mspace
    0.33
    est
    0.31
     c
    0.30
     s
    0.30
    </strong>
    0.30
    atura
    0.29
    </h3>
    0.29
     nearly
    0.29
    Activations Density 0.003%

    No Known Activations