© 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. 0-CLT-HP
    7. 90832
    Prev
    Next
    INDEX
    Explanations

    social networking media

    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
     igång
    -0.82
    moiselle
    -0.66
    hatenablog
    -0.66
     antaranya
    -0.63
    Regs
    -0.63
     médias
    -0.63
    alnız
    -0.63
    PointerException
    -0.62
     Houſe
    -0.60
     varargin
    -0.60
    POSITIVE LOGITS
    पया
    0.59
     worthy
    0.56
    ///</
    0.44
     кӀ
    0.42
    amoan
    0.42
     couver
    0.42
    ,
    0.41
     doce
    0.40
    UnitTesting
    0.40
    cusión
    0.40
    Activations Density 0.738%

    No Known Activations