© 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. 0-CLT-HP
    4. 43558
    Prev
    Next
    INDEX
    Explanations

    actions being performed

    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
     comigo
    -0.69
     démocr
    -0.68
     löyty
    -0.68
     stället
    -0.67
     tarko
    -0.66
     conmigo
    -0.65
     igång
    -0.65
     noires
    -0.63
     anún
    -0.63
    guien
    -0.63
    POSITIVE LOGITS
     the
    1.70
     a
    1.33
     an
    1.22
     their
    1.20
     some
    1.16
     those
    1.08
     its
    1.03
     this
    1.01
     his
    1.00
     any
    1.00
    Activations Density 0.044%

    No Known Activations