© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4328
    Prev
    Next
    INDEX
    Explanations

    years

    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
     незавершена
    -0.70
    matchCondition
    -0.52
    ]]);
    -0.44
    tvguidetime
    -0.44
    ").
    -0.44
    ]").
    -0.43
    managers
    -0.43
    ']").
    -0.42
     gears
    -0.42
    Doch
    -0.41
    POSITIVE LOGITS
    MockMvc
    0.68
    ьаж
    0.65
     Âge
    0.65
     consultato
    0.65
     autorytatywna
    0.64
     חיצוניים
    0.62
    éu
    0.60
     vägen
    0.60
     transfieras
    0.60
    graphiques
    0.59
    Activations Density 0.002%

    No Known Activations