© 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. 0-CLT-HP
    7. 41544
    Prev
    Next
    INDEX
    Explanations

    Set, Make

    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
     We
    -0.68
     Get
    -0.65
     Find
    -0.49
     In
    -0.46
     Let
    -0.46
    :+:
    -0.43
     pinulongan
    -0.43
    Become
    -0.42
    .
    -0.42
     Set
    -0.41
    POSITIVE LOGITS
     Reſ
    0.96
     Anſ
    0.95
     Monfieur
    0.92
     faſt
    0.90
     Diſ
    0.89
     myſelf
    0.87
     Conſ
    0.85
     Majefty
    0.85
    ſelf
    0.82
     purpoſe
    0.82
    Activations Density 0.039%

    No Known Activations