© 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. 96
    Prev
    Next
    INDEX
    Explanations

    Lists and considerations

    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
    DockStyle
    -0.65
     createState
    -0.56
    athione
    -0.45
     keyCode
    -0.45
    AddTagHelper
    -0.44
    født
    -0.44
    BindingResult
    -0.43
    }}"
    -0.42
    uinal
    -0.42
    eezy
    -0.41
    POSITIVE LOGITS
     that
    1.00
    <bos>
    0.99
    that
    0.76
    पया
    0.70
     everybody
    0.66
     everyone
    0.65
    +#+#
    0.64
     enfans
    0.63
     they
    0.63
     étoit
    0.60
    Activations Density 0.006%

    No Known Activations