© 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. 4-CLT-HP
    7. 4904
    Prev
    Next
    INDEX
    Explanations

    computer/technical text

    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
    ReusableCell
    -0.52
    +#+#
    -0.50
    CloseOperation
    -0.47
     mess
    -0.46
    PreferredItem
    -0.43
     parteci
    -0.42
    #+#
    -0.41
    didSet
    -0.41
     SEDS
    -0.41
    er
    -0.40
    POSITIVE LOGITS
     esternos
    0.72
    Попис
    0.59
     DISC
    0.57
    |]
    0.57
     lenker
    0.56
    Personendaten
    0.56
     invokingState
    0.56
    клопе
    0.54
     Buyer
    0.54
     Discovery
    0.54
    Activations Density 0.002%

    No Known Activations