© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96479
    Prev
    Next
    INDEX
    Explanations

    technical/quantitative data

    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
    InjectMocks
    -0.59
    PointerException
    -0.59
     BoxDecoration
    -0.53
    indd
    -0.52
    <bos>
    -0.52
     nakalista
    -0.50
    nungs
    -0.49
    IInterface
    -0.49
    TargetException
    -0.48
    DECREF
    -0.48
    POSITIVE LOGITS
     متعلقه
    0.88
     resourceCulture
    0.59
     kiệm
    0.54
    exitRule
    0.54
    principalTable
    0.53
    :][
    0.53
    LayoutConstraint
    0.52
     niedersachsen
    0.50
     IBRARY
    0.50
    AsUp
    0.49
    Activations Density 0.016%

    No Known Activations