© 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. 5-CLT-HP
    7. 5347
    Prev
    Next
    INDEX
    Explanations

    north

    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
     REASONS
    -0.50
    쟁
    -0.49
    ønne
    -0.49
    Reasons
    -0.47
    relse
    -0.47
     Der
    -0.46
    laughter
    -0.44
    jsonPath
    -0.44
     hyperplasia
    -0.43
    رسد
    -0.43
    POSITIVE LOGITS
     تضيفلها
    0.84
    principalTable
    0.74
    VIAF
    0.67
    SequentialGroup
    0.64
    DIPSETTING
    0.63
    EndProject
    0.62
    AndEndTag
    0.59
    EndGlobalSection
    0.58
    GeoNames
    0.58
    PropertyChanging
    0.57
    Activations Density 0.002%

    No Known Activations