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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14233
    Prev
    Next
    INDEX
    Explanations

    circuits

    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
     circuit
    -0.73
    ⓘ
    -0.62
     Circuit
    -0.60
    enumii
    -0.59
    IUrlHelper
    -0.58
    cred
    -0.56
    RepeatedField
    -0.55
    circuit
    -0.52
    ipto
    -0.50
    WireFormat
    -0.50
    POSITIVE LOGITS
    URLException
    0.56
     fallu
    0.54
    Portale
    0.52
    berdayakan
    0.51
     tartalomajánló
    0.51
    NameInMap
    0.51
     CGSize
    0.50
    matician
    0.50
    usion
    0.48
    vericks
    0.48
    Activations Density 0.033%

    No Known Activations