© 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. 3759
    Prev
    Next
    INDEX
    Explanations

    commas and "J"

    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>
    -0.81
    oredCriteria
    -0.74
    errHandler
    -0.67
     itſelf
    -0.63
     himſelf
    -0.60
    ſelf
    -0.57
    enumii
    -0.57
     myſelf
    -0.56
     raiſ
    -0.56
     whoſe
    -0.55
    POSITIVE LOGITS
    Scénario
    0.46
    étation
    0.45
     GenerationType
    0.45
    cula
    0.44
    CrossRef
    0.44
     QtCore
    0.43
    writerow
    0.42
    mål
    0.42
     Population
    0.42
     Serializable
    0.41
    Activations Density 0.022%

    No Known Activations