© 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. 1063
    Prev
    Next
    INDEX
    Explanations

    th

    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
    ″
    -1.00
    ′
    -0.77
    erals
    -0.65
    ItemBackground
    -0.63
     disambiguazione
    -0.62
     NUKAT
    -0.59
     torchvision
    -0.59
    jsonwebtoken
    -0.58
     setuptools
    -0.58
     agrí
    -0.58
    POSITIVE LOGITS
    top
    0.55
    setopt
    0.52
    DotNetBar
    0.50
    ⮕
    0.50
    lines
    0.48
    AndEndTag
    0.48
     []:
    0.47
    self
    0.46
     bedient
    0.44
    roots
    0.44
    Activations Density 0.795%

    No Known Activations