© 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. 92656
    Prev
    Next
    INDEX
    Explanations

    changes and development

    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
     Expanded
    -0.96
     expanded
    -0.86
     Expanding
    -0.85
     normaux
    -0.84
    Expanded
    -0.81
     fotografico
    -0.81
    expanding
    -0.79
    ostante
    -0.78
     tartalomajánló
    -0.78
     Debris
    -0.77
    POSITIVE LOGITS
     home
    0.60
     صوتيه
    0.59
     and
    0.58
     man
    0.57
     under
    0.56
     for
    0.55
    LookAnd
    0.55
     following
    0.53
     UP
    0.52
     two
    0.50
    Activations Density 0.118%

    No Known Activations