© 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. 5-CLT-HP
    7. 92561
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ItemLayout
    -0.64
     the
    -0.59
    Ikus
    -0.56
     erbjud
    -0.56
     logistique
    -0.53
     الرياضيه
    -0.52
     سكانية
    -0.50
     geldig
    -0.50
    IsMutable
    -0.49
     gräns
    -0.48
    POSITIVE LOGITS
    fastjson
    0.61
     pinulongan
    0.57
     suddenly
    0.56
    BindingResult
    0.54
    ioutil
    0.51
    NOPQRST
    0.51
    urlopen
    0.50
     quickly
    0.49
    FirstResponder
    0.48
    dehyde
    0.48
    Activations Density 0.005%

    No Known Activations