© 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. 4-CLT-HP
    7. 4905
    Prev
    Next
    INDEX
    Explanations

    the

    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
     unknownFields
    -0.56
    endaftaran
    -0.56
    }{*}{}
    -0.54
    undred
    -0.54
    reuung
    -0.51
    polation
    -0.50
    amaha
    -0.50
    intenance
    -0.49
    hastly
    -0.49
    Personensuche
    -0.49
    POSITIVE LOGITS
     arşivlendi
    0.65
    
    0.59
     propOrder
    0.58
    ia
    0.56
    sed
    0.56
    oy
    0.54
    eps
    0.53
    ner
    0.53
    ul
    0.52
    als
    0.52
    Activations Density 0.006%

    No Known Activations