© 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. 0-CLT-HP
    7. 92412
    Prev
    Next
    INDEX
    Explanations

    from

    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
    parsedMessage
    -0.70
     equalization
    -0.69
    ovatel
    -0.69
    +#+#
    -0.68
     ProtoMessage
    -0.68
    ContentAlignment
    -0.66
    tagHelperRunner
    -0.65
    rungsseite
    -0.64
     ſhe
    -0.63
     Soyez
    -0.63
    POSITIVE LOGITS
     An
    0.45
    Portale
    0.45
     AN
    0.43
    Hozzáférés
    0.43
     consultato
    0.43
     a
    0.42
     to
    0.42
     an
    0.42
     Account
    0.40
     originalen
    0.40
    Activations Density 0.632%

    No Known Activations