© 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. 42108
    Prev
    Next
    INDEX
    Explanations

    cutting-edge

    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
    b
    -0.57
    f
    -0.56
     to
    -0.55
    os
    -0.51
    bs
    -0.49
    e
    -0.48
    ce
    -0.47
    i
    -0.47
    j
    -0.47
     -
    -0.46
    POSITIVE LOGITS
     Reſ
    1.19
     Majefty
    1.18
     Anſ
    1.16
     Houſe
    1.13
     Diſ
    1.12
     ―――――
    1.10
     Monfieur
    1.07
     Eſ
    1.04
     pleaſure
    1.04
     Efq
    0.99
    Activations Density 0.466%

    No Known Activations