© 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. 2848
    Prev
    Next
    INDEX
    Explanations

    absence

    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
    holtz
    -0.48
     Grab
    -0.48
    IMAN
    -0.47
    otoxin
    -0.46
    rai
    -0.45
     of
    -0.45
    ASYNC
    -0.44
     difference
    -0.44
    Grab
    -0.43
     analogue
    -0.43
    POSITIVE LOGITS
    İstinadlar
    0.75
    +#+
    0.72
     للاسماء
    0.71
    хьтан
    0.65
     SEDS
    0.63
    Personensuche
    0.59
     ErrIntOverflow
    0.57
     hjemme
    0.57
    TRAILING
    0.57
     asupra
    0.56
    Activations Density 0.001%

    No Known Activations