© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2774
    Prev
    Next
    INDEX
    Explanations

    .

    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
    PointerException
    -0.66
     &___
    -0.65
    ToFit
    -0.59
     Bull
    -0.58
    migo
    -0.56
    RectangleBorder
    -0.53
    ienta
    -0.53
    /");
    -0.52
    Bullshit
    -0.50
     Understand
    -0.50
    POSITIVE LOGITS
    Izvori
    0.50
    bbene
    0.48
    Referències
    0.47
     fourrure
    0.46
    Réalisation
    0.44
     mostaza
    0.43
     يتيمه
    0.43
    Réponse
    0.43
     brave
    0.42
    Източници
    0.42
    Activations Density 0.002%

    No Known Activations