© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11333
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    bo
    -1.18
    Hentet
    -0.73
     Bo
    -0.72
    Bo
    -0.65
     bo
    -0.65
     Савезне
    -0.63
    BO
    -0.61
     correctes
    -0.58
     énergé
    -0.57
     سكانية
    -0.56
    POSITIVE LOGITS
    encodeWith
    0.53
    PyTuple
    0.49
    Url
    0.49
    VersionUID
    0.48
    Lith
    0.45
     lachen
    0.45
    ).__
    0.44
    Kon
    0.44
    hacia
    0.44
    郎
    0.44
    Activations Density 0.079%

    No Known Activations