© 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. 43115
    Prev
    Next
    INDEX
    Explanations

    only

    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
    only
    -0.82
     only
    -0.79
    ONLY
    -0.74
     ONLY
    -0.73
    Parcelize
    -0.73
     ddelweddau
    -0.66
     resourceCulture
    -0.65
    Only
    -0.62
    فقط
    -0.60
    Fcn
    -0.59
    POSITIVE LOGITS
     inwardly
    0.56
     Leopold
    0.56
     Agamemnon
    0.51
     
    0.49
     David
    0.48
    <bos>
    0.46
     Richelieu
    0.45
    kespea
    0.45
     verbally
    0.45
     Moslem
    0.45
    Activations Density 0.026%

    No Known Activations