© 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. 93276
    Prev
    Next
    INDEX
    Explanations

    Names

    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
     Die
    -0.84
     die
    -0.84
     az
    -0.82
     Az
    -0.76
     Mar
    -0.74
     Sie
    -0.71
     a
    -0.65
     Ma
    -0.65
     El
    -0.63
     Le
    -0.63
    POSITIVE LOGITS
     myſelf
    1.59
     Monfieur
    1.55
     itſelf
    1.54
     Theſe
    1.52
     Houſe
    1.48
     Jefus
    1.48
     Majefty
    1.46
     Anſ
    1.42
     Shakspeare
    1.40
     Reſ
    1.39
    Activations Density 1.160%

    No Known Activations