© 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. 1-CLT-HP
    4. 804
    Prev
    Next
    INDEX
    Explanations

    layer

    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
     للتو
    -0.47
    uç
    -0.46
     Money
    -0.45
     bico
    -0.44
     Alford
    -0.44
     صوتيه
    -0.41
    stonia
    -0.41
     loft
    -0.41
     ad
    -0.41
    Tikang
    -0.41
    POSITIVE LOGITS
    protoc
    0.61
    peq
    0.60
    \{\\
    0.59
    BufferException
    0.58
    UnsafeEnabled
    0.56
    OGND
    0.55
     œufs
    0.55
    NUMX
    0.54
     évit
    0.54
    GraphicsUnit
    0.53
    Activations Density 0.022%

    No Known Activations