© 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. 12516
    Prev
    Next
    INDEX
    Explanations

    of

    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
     corridors
    -0.67
    periods
    -0.60
     courbe
    -0.60
     conventions
    -0.58
     cycles
    -0.56
     durations
    -0.56
     commitments
    -0.56
     curves
    -0.56
    ‘
    -0.55
     complexes
    -0.54
    POSITIVE LOGITS
    +#+#
    0.94
    ftagPool
    0.65
     surla
    0.65
    Personendaten
    0.65
    LookAnd
    0.62
    findpost
    0.60
    MENAFN
    0.59
    KURZBESCHREIBUNG
    0.59
    ReusableCell
    0.58
     Roskov
    0.56
    Activations Density 0.005%

    No Known Activations