© 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. 0-CLT-HP
    7. 91126
    Prev
    Next
    INDEX
    Explanations

    code, programming

    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
    tims
    -1.77
    rrggbb
    -0.74
    ftagPool
    -0.69
    contentLoaded
    -0.66
    fjspx
    -0.65
    OGND
    -0.64
     سكانية
    -0.64
     pinulongan
    -0.63
    styleType
    -0.63
     متعلقه
    -0.63
    POSITIVE LOGITS
    }`).
    0.44
     høre
    0.42
     sprá
    0.41
     całość
    0.41
     ворот
    0.40
    icol
    0.40
     skrift
    0.40
     accrue
    0.39
     takiej
    0.39
     tuturor
    0.39
    Activations Density 0.083%

    No Known Activations