© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 900
    Prev
    Next
    INDEX
    Explanations

    centric

    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
    Geplaatst
    -0.77
     Roskov
    -0.62
    Sequ
    -0.60
     Monfieur
    -0.59
    AddField
    -0.58
     الحره
    -0.56
    hoeddwyd
    -0.56
    AlterField
    -0.55
     يتيمه
    -0.54
     himſelf
    -0.53
    POSITIVE LOGITS
    er
    0.60
    twimg
    0.57
    ers
    0.56
    SharedDtor
    0.50
    ing
    0.47
    outs
    0.45
     ORIGIN
    0.45
    /**/*.
    0.45
    teenth
    0.44
     Origin
    0.44
    Activations Density 0.011%

    No Known Activations