© 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. 4-CLT-HP
    7. 3536
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    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
    RemoteException
    -0.60
     onBind
    -0.57
     snippetHide
    -0.56
    iama
    -0.55
    oyle
    -0.52
    tomia
    -0.52
     tenth
    -0.52
     exclusion
    -0.51
    Życiorys
    -0.50
     fifteenth
    -0.50
    POSITIVE LOGITS
     незавершена
    0.67
     tutti
    0.52
    ward
    0.50
    RTEE
    0.47
     all
    0.47
     tutte
    0.46
    lında
    0.46
    Tutti
    0.44
     We
    0.44
    :"-"`
    0.44
    Activations Density 0.002%

    No Known Activations