© 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. 73456
    Prev
    Next
    INDEX
    Explanations

    crystal

    np_max-act-logits · gemini-2.0-flash
    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
    tagHelperRunner
    -0.71
    NUMX
    -0.70
    ˏ
    -0.68
    estacks
    -0.63
    drawal
    -0.61
     TType
    -0.60
    omiast
    -0.59
    TSC
    -0.59
    cplusplus
    -0.59
     Velcro
    -0.59
    POSITIVE LOGITS
     dec
    0.65
     crystal
    0.57
     gué
    0.55
     cru
    0.53
    cru
    0.51
    v
    0.49
     kristal
    0.48
     cara
    0.48
     shot
    0.47
    crystal
    0.47
    Activations Density 0.000%

    No Known Activations