© 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. 4-CLT-HP
    7. 132
    Prev
    Next
    INDEX
    Explanations

    code and legal documents

    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
     nakalista
    -0.93
    +#+#
    -0.83
     <<<<<<<<<<<<<<
    -0.80
     dinosaurs
    -0.75
    awtextra
    -0.75
     remission
    -0.74
     hula
    -0.73
     paddles
    -0.72
     archer
    -0.70
     golfers
    -0.70
    POSITIVE LOGITS
     églises
    0.42
     jouets
    0.41
    <bos>
    0.39
     carreaux
    0.39
     säll
    0.36
     dépens
    0.36
     lèvres
    0.36
     dizaines
    0.35
     pauvres
    0.35
     rayures
    0.35
    Activations Density 0.030%

    No Known Activations