© 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. 76482
    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
    +#+#
    -0.64
    Datuak
    -0.56
    __':
    -0.56
    ContextHolder
    -0.54
     صوتيه
    -0.52
    reathe
    -0.52
    __':
    -0.51
    Réponse
    -0.50
     ©️
    -0.50
    ########.
    -0.49
    POSITIVE LOGITS
    OrBuilder
    0.58
    webElementXpaths
    0.55
     CreateTagHelper
    0.54
     standing
    0.52
    FieldBuilder
    0.52
    lorette
    0.50
    hyrchwyd
    0.50
    canestro
    0.49
     HttpNotFound
    0.48
    LookAnd
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.