© 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. 5-CLT-HP
    7. 2929
    Prev
    Next
    INDEX
    Explanations

    the

    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
    IntoConstraints
    -0.57
    ReusableCell
    -0.57
    RegistryLite
    -0.57
    atoday
    -0.56
     pinulongan
    -0.56
    bootstrapcdn
    -0.54
     famí
    -0.53
     Normdatei
    -0.53
    andReturn
    -0.51
    Hochspringen
    -0.51
    POSITIVE LOGITS
     brain
    0.45
     Détails
    0.45
    piac
    0.44
    Recap
    0.44
    vänd
    0.43
    /**
    0.43
    ğine
    0.42
    BRD
    0.42
    GID
    0.42
     kohta
    0.42
    Activations Density 0.001%

    No Known Activations