© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 811
    Prev
    Next
    INDEX
    Explanations

    beings

    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
     eût
    -0.63
    tonsoft
    -0.60
    themselves
    -0.58
     themselves
    -0.57
     capuz
    -0.54
    their
    -0.53
    zī
    -0.52
    ")->
    -0.52
     hendak
    -0.51
     honom
    -0.50
    POSITIVE LOGITS
     BorderSide
    0.56
    Tembelea
    0.49
    ására
    0.49
     BIBSYS
    0.49
     geh
    0.49
     Beller
    0.48
     gynhyrchwyd
    0.47
     createSlice
    0.46
     aDecoder
    0.46
    RTDA
    0.46
    Activations Density 0.000%

    No Known Activations