© 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. 0-CLT-HP
    7. 92914
    Prev
    Next
    INDEX
    Explanations

    termination

    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
     termination
    -1.39
     terminated
    -1.36
     terminating
    -1.35
     termin
    -1.32
     terminate
    -1.30
    termination
    -1.24
    termin
    -1.17
    terminated
    -1.14
     Termination
    -1.13
     TERMIN
    -1.09
    POSITIVE LOGITS
    transQ
    0.56
    ագրություններ
    0.52
     onPostExecute
    0.52
     rayures
    0.50
     Shallow
    0.50
    êté
    0.50
     cork
    0.47
     ListTile
    0.47
     Gegenteil
    0.47
    فحة
    0.47
    Activations Density 0.164%

    No Known Activations