© 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. 3320
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Italie
    -0.59
    kill
    -0.47
     igjen
    -0.47
    ểm
    -0.46
     riso
    -0.46
     smaak
    -0.46
    rungsseite
    -0.45
     оригіналу
    -0.45
     ether
    -0.44
    TabIndex
    -0.43
    POSITIVE LOGITS
     Савезне
    0.69
    >--}}
    0.69
    EnableWeb
    0.63
    webElementXpaths
    0.63
    ]$}
    0.61
    posedge
    0.60
    bibinfo
    0.59
    RepeatedField
    0.59
    ]")]
    0.58
    leuth
    0.58
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.