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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91177
    Prev
    Next
    INDEX
    Explanations

    places and regions

    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
    XmlAccessorType
    -0.80
    клопе
    -0.77
     vectorielle
    -0.76
     AssemblyTitle
    -0.75
     vectorielles
    -0.74
    protetor
    -0.73
     étoient
    -0.73
     valable
    -0.72
     financières
    -0.71
    jsxFileName
    -0.71
    POSITIVE LOGITS
     des
    0.48
     CUR
    0.45
    irs
    0.44
     ARC
    0.44
     control
    0.41
    aa
    0.41
    ier
    0.41
    ]^{
    0.41
     road
    0.40
     Huck
    0.40
    Activations Density 0.066%

    No Known Activations