© 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. 0-CLT-HP
    7. 42720
    Prev
    Next
    INDEX
    Explanations

    provided

    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
     étoient
    -0.80
    ();?>
    -0.74
     médicaux
    -0.69
     nuages
    -0.69
     étoit
    -0.68
     mauvaises
    -0.68
     varandra
    -0.67
     precisione
    -0.67
     singoli
    -0.66
     véritables
    -0.66
    POSITIVE LOGITS
     in
    0.67
    <bos>
    0.54
     injecting
    0.48
     separ
    0.47
     hiding
    0.47
     indoors
    0.47
     terrest
    0.46
     throughout
    0.46
     licking
    0.44
     kicking
    0.44
    Activations Density 0.193%

    No Known Activations