© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 409
    Prev
    Next
    INDEX
    Explanations

    ated

    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
    olese
    -0.51
     Obrador
    -0.50
    expandindo
    -0.46
     pendekatan
    -0.46
     approche
    -0.45
    Équipe
    -0.45
     Egl
    -0.45
    lodash
    -0.45
    verständlich
    -0.45
    SPATH
    -0.44
    POSITIVE LOGITS
    ukunfts
    0.64
    saraba
    0.59
    хьтан
    0.57
    prüche
    0.57
    Javadoc
    0.56
    Życiorys
    0.56
    CloseOperation
    0.56
    वार
    0.56
    сылкі
    0.55
    ParallelGroup
    0.54
    Activations Density 0.029%

    No Known Activations