© 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. 984
    Prev
    Next
    INDEX
    Explanations

    blacksmith

    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
    ContentAsync
    -0.82
    endphp
    -0.67
    styleType
    -0.67
     pleaſure
    -0.65
    dymyr
    -0.65
    IntoConstraints
    -0.63
     onPostExecute
    -0.61
     contextLoads
    -0.61
    CppMethod
    -0.61
     IEnumerator
    -0.60
    POSITIVE LOGITS
    ^=
    0.47
    geblich
    0.47
    whip
    0.46
     itinéraires
    0.42
     ust
    0.42
    urada
    0.41
    ۜ
    0.41
    Fay
    0.41
    bės
    0.39
     mor
    0.39
    Activations Density 0.031%

    No Known Activations