© 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. 5-CLT-HP
    4. 96166
    Prev
    Next
    INDEX
    Explanations

    Technical and research snippets

    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
    enumi
    -0.79
    parsedMessage
    -0.71
    addCriterion
    -0.66
    Viitteet
    -0.63
    sidemargin
    -0.62
    ".$_
    -0.61
    WebElementEntity
    -0.61
    schnitt
    -0.59
    IVEREF
    -0.59
     CanadaChoose
    -0.58
    POSITIVE LOGITS
     RIA
    0.43
    áus
    0.43
    illir
    0.42
     IRIS
    0.41
     STAM
    0.40
     GMAT
    0.40
     Gall
    0.39
    Nth
    0.39
    <bos>
    0.39
    level
    0.39
    Activations Density 0.003%

    No Known Activations