© 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. 1-CLT-HP
    7. 46278
    Prev
    Next
    INDEX
    Explanations

    Code/Copyright/Organization references

    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
     noDo
    -0.59
    oa̍t
    -0.56
    InteropServices
    -0.54
     Савезне
    -0.53
     Bra
    -0.52
    帖最后由
    -0.51
    uxxxx
    -0.51
    التالي
    -0.50
    +#+#
    -0.50
     betweenstory
    -0.49
    POSITIVE LOGITS
    den
    0.54
    alad
    0.54
    iss
    0.49
    dat
    0.47
    gen
    0.47
    dle
    0.46
    alade
    0.46
    gy
    0.46
    dung
    0.46
    ger
    0.45
    Activations Density 0.024%

    No Known Activations