© 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. 4-CLT-HP
    7. 1594
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · 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
    Rhestr
    -0.63
    TagMode
    -0.62
    unhofer
    -0.55
    angsaan
    -0.54
     HasFactory
    -0.54
    InitVars
    -0.53
    sizeCache
    -0.53
    íslu
    -0.52
    twimg
    -0.52
    zzleHttp
    -0.49
    POSITIVE LOGITS
    ValueStyle
    0.65
    cshtml
    0.58
     is
    0.55
     beneath
    0.52
     asks
    0.52
     another
    0.52
     identifies
    0.51
    󠁿
    0.51
     brings
    0.51
     hangs
    0.50
    Activations Density 0.008%

    No Known Activations