© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13899
    Prev
    Next
    INDEX
    Explanations

    National

    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
    knię
    -0.45
    DebuggerStep
    -0.43
    HtmlAttribute
    -0.43
    是对
    -0.42
    detectChanges
    -0.42
    Planet
    -0.42
    newBuilder
    -0.42
     antioxidant
    -0.41
    CGRectMake
    -0.41
    ]%
    -0.41
    POSITIVE LOGITS
    Autoritní
    0.64
    MessageTagHelper
    0.62
     Normdatei
    0.60
    featureID
    0.59
    inafter
    0.58
     Subpart
    0.58
     Tit
    0.58
    lineTo
    0.57
    kháu
    0.57
     linkovi
    0.57
    Activations Density 0.014%

    No Known Activations