© 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. 95228
    Prev
    Next
    INDEX
    Explanations

    code and numbers

    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
    verwijspagina
    -0.64
    dailymail
    -0.64
    hoga
    -0.63
    äiv
    -0.62
    OGND
    -0.59
    lixir
    -0.59
    dirond
    -0.57
    zyż
    -0.57
     Shaksp
    -0.57
    phora
    -0.56
    POSITIVE LOGITS
    EndInit
    0.57
     سكانية
    0.46
    ValueStyle
    0.46
     CanadaChoose
    0.44
    GraphicsUnit
    0.43
    tagHelperRunner
    0.43
     KIT
    0.42
    ReusableCell
    0.42
     Kit
    0.41
    "]),
    0.41
    Activations Density 0.002%

    No Known Activations