© 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. 77652
    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
    OGND
    -0.70
    ExtendWith
    -0.66
    TagMode
    -0.65
    CodedInputStream
    -0.64
     doigts
    -0.63
    хьтан
    -0.61
    ResponseWriter
    -0.59
     internetowa
    -0.57
    DebuggerNonUser
    -0.57
     lèvres
    -0.56
    POSITIVE LOGITS
    skapet
    0.48
     sint
    0.46
     oras
    0.44
    уза
    0.44
     Lagrange
    0.43
     wz
    0.43
    ræ
    0.43
     fibrillation
    0.43
    Хро
    0.43
     venga
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.