© 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. 73210
    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
     béné
    -0.55
     réguli
    -0.54
     scolaires
    -0.53
     cappello
    -0.53
     cérami
    -0.52
    IndentedString
    -0.52
    _",
    -0.49
     dignité
    -0.47
     longues
    -0.47
    المكان
    -0.47
    POSITIVE LOGITS
    uxxxx
    0.70
    principalTable
    0.58
    deka
    0.55
    RTCF
    0.55
     consultato
    0.55
     autom
    0.51
     GUID
    0.50
    mybatisplus
    0.50
    idjan
    0.50
    izze
    0.49
    Activations Density 0.005%

    No Known Activations