© 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. 3427
    Prev
    Next
    INDEX
    Explanations

    (

    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
     kasarigan
    -0.73
    protoimpl
    -0.71
    StructEnd
    -0.65
     ModelExpression
    -0.62
    GMENT
    -0.57
    uxxxx
    -0.57
     noDo
    -0.55
    GEBURTSDATUM
    -0.54
    OGND
    -0.53
    kháu
    -0.53
    POSITIVE LOGITS
     getItemId
    0.54
     mourut
    0.53
    awtextra
    0.51
    ReadKey
    0.51
     misura
    0.50
    出版年
    0.50
     eût
    0.49
    Αν
    0.48
    f
    0.47
    VolleyError
    0.47
    Activations Density 0.022%

    No Known Activations