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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 95256
    Prev
    Next
    INDEX
    Explanations

    3

    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
     للمعارف
    -0.62
     صوتيه
    -0.51
     calldata
    -0.49
    InMillis
    -0.47
     ContentValues
    -0.44
    ciorys
    -0.43
     model
    -0.41
    textAppearance
    -0.41
     hashCode
    -0.40
    =<?
    -0.40
    POSITIVE LOGITS
    клопе
    0.64
    arakhand
    0.64
    tableFuture
    0.63
    orsese
    0.63
    पया
    0.61
     незавершена
    0.58
    ghalaya
    0.58
    uruhan
    0.56
     aéri
    0.55
     découver
    0.55
    Activations Density 0.000%

    No Known Activations