© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3500
    Prev
    Next
    INDEX
    Explanations

    it

    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
    <bos>
    -0.52
    +:+
    -0.52
    given
    -0.50
    epiece
    -0.49
    GridColumn
    -0.48
     ostavi
    -0.45
     promont
    -0.45
     mít
    -0.45
     given
    -0.44
    campal
    -0.44
    POSITIVE LOGITS
     esternos
    0.77
    发表于
    0.72
    riwal
    0.70
    новниш
    0.64
    LookAnd
    0.64
    complexContent
    0.63
     looks
    0.63
    Portale
    0.61
    NewUrlParser
    0.61
    ArgsConstructor
    0.61
    Activations Density 0.005%

    No Known Activations