© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15285
    Prev
    Next
    INDEX
    Explanations

    one of them

    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
     work
    -0.60
     selves
    -0.52
    selves
    -0.51
    çoivent
    -0.44
    IDADE
    -0.44
    mity
    -0.43
     horri
    -0.43
    maler
    -0.42
    laze
    -0.42
     znajdują
    -0.42
    POSITIVE LOGITS
    StoryboardSegue
    0.90
     pinulongan
    0.84
     tartalomajánló
    0.79
    Personensuche
    0.75
    findpost
    0.73
     /\.(
    0.71
    featureID
    0.69
    ImageContext
    0.68
     GenerationType
    0.68
    IsContent
    0.66
    Activations Density 0.094%

    No Known Activations