© 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. 1-CLT-HP
    7. 526
    Prev
    Next
    INDEX
    Explanations

    explain

    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
    __*/
    -0.84
     Audiodateien
    -0.81
    UserScript
    -0.74
    expandindo
    -0.70
    Javadoc
    -0.69
    IGraphics
    -0.69
    URLException
    -0.69
    ########.
    -0.69
     الحره
    -0.68
    izr
    -0.67
    POSITIVE LOGITS
     to
    0.57
    ljiv
    0.44
     more
    0.40
    PreExecute
    0.39
     Blood
    0.39
    ci
    0.38
    DebuggerStep
    0.38
    рын
    0.37
     Fully
    0.37
     Feeling
    0.37
    Activations Density 0.011%

    No Known Activations