© 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. 1-CLT-HP
    7. 14293
    Prev
    Next
    INDEX
    Explanations

    er

    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
     vérit
    -0.62
     déchir
    -0.57
    SourceChecksum
    -0.57
    ">//
    -0.56
    AxisAlignment
    -0.56
     amitié
    -0.55
     längre
    -0.54
     blevet
    -0.54
     kommet
    -0.54
     détruire
    -0.53
    POSITIVE LOGITS
    thered
    0.55
     contd
    0.51
     among
    0.50
    abag
    0.49
    eradish
    0.48
    patine
    0.47
    principalTable
    0.47
    cove
    0.47
    ibase
    0.47
     Beale
    0.46
    Activations Density 0.072%

    No Known Activations