© 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. 20-CLT-HP
    7. 76284
    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
    habhar
    -0.56
    αρ
    -0.54
     Fort
    -0.51
     Wikispecies
    -0.51
     coffee
    -0.48
    setVerticalGroup
    -0.48
    fles
    -0.48
     Coffee
    -0.47
    @[+][
    -0.47
    リーブ
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    0.78
    日閲覧
    0.68
    MENAFN
    0.66
    StoryboardSegue
    0.63
    MessageTagHelper
    0.57
     noDo
    0.57
    GEBURTS
    0.56
    ]';
    0.56
    lysm
    0.54
    AxisAlignment
    0.53
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.