© 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. 5-CLT-HP
    7. 96212
    Prev
    Next
    INDEX
    Explanations

    personal expression/limitations

    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
     الحره
    -0.69
    SharedCtor
    -0.63
    seamnă
    -0.63
    webElementXpaths
    -0.62
    ligibility
    -0.58
    Koordinaten
    -0.54
    ekš
    -0.54
    +#+
    -0.52
     للاسماء
    -0.51
     trở
    -0.50
    POSITIVE LOGITS
     from
    0.58
    GetMapping
    0.51
    RegressionTest
    0.48
     Prize
    0.46
     AssemblyCulture
    0.46
     to
    0.45
     axio
    0.45
     pracu
    0.45
    pruch
    0.44
    Prize
    0.43
    Activations Density 0.001%

    No Known Activations