© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13196
    Prev
    Next
    INDEX
    Explanations

    Code/identifiers

    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
     köz
    -0.52
     c
    -0.47
     detalj
    -0.44
    之一
    -0.42
     an
    -0.42
    途
    -0.41
     antaranya
    -0.41
    publicain
    -0.41
     tø
    -0.41
     “
    -0.40
    POSITIVE LOGITS
    parsedMessage
    1.10
    esModule
    0.91
     NSCoder
    0.90
    NameInMap
    0.88
    TestingModule
    0.87
    +#+#
    0.86
    contentLoaded
    0.84
     MainAxisSize
    0.82
    ValueStyle
    0.81
    addCriterion
    0.79
    Activations Density 0.023%

    No Known Activations