© 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. 4-CLT-HP
    7. 1991
    Prev
    Next
    INDEX
    Explanations

    bands, strips of material

    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
    Lähteet
    -0.41
    zama
    -0.36
    ✭
    -0.36
    IMATE
    -0.35
    Meister
    -0.35
     suficientes
    -0.34
    remoto
    -0.34
    حياته
    -0.34
     jefes
    -0.34
    cry
    -0.33
    POSITIVE LOGITS
     EconPapers
    1.02
    Personendaten
    0.84
    TypedDataSet
    0.84
    StructEnd
    0.82
    +#+
    0.76
    tagHelperRunner
    0.75
    يميديا
    0.75
    WithIOException
    0.72
    iecie
    0.72
     تضيفلها
    0.71
    Activations Density 0.004%

    No Known Activations