© 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. 13916
    Prev
    Next
    INDEX
    Explanations

    stopping

    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
     stopped
    -0.51
    expandindo
    -0.49
    Tikang
    -0.48
    ory
    -0.45
    ity
    -0.45
    imen
    -0.44
    phe
    -0.44
    ToPoint
    -0.43
    째
    -0.43
    ile
    -0.43
    POSITIVE LOGITS
    :✨
    0.81
     كومونز
    0.77
     урна
    0.67
    AccessorTable
    0.64
     autorytatywna
    0.63
     WaitForSeconds
    0.61
    oprot
    0.60
    abetes
    0.60
     doInBackground
    0.59
     kaynağından
    0.59
    Activations Density 0.017%

    No Known Activations