© 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. 5-CLT-HP
    7. 2143
    Prev
    Next
    INDEX
    Explanations

    academic papers

    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
     and
    -0.45
     five
    -0.44
     is
    -0.43
     ex
    -0.43
     get
    -0.43
     lead
    -0.42
     both
    -0.42
    idis
    -0.41
     several
    -0.41
     don
    -0.40
    POSITIVE LOGITS
    Parcelize
    0.82
    دانشنامهٔ
    0.80
    CopyWith
    0.71
     تضيفلها
    0.71
    ########.
    0.70
    AccessorTable
    0.69
    EndContext
    0.69
     protoimpl
    0.68
    awtextra
    0.67
    localctx
    0.65
    Activations Density 0.029%

    No Known Activations