© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91337
    Prev
    Next
    INDEX
    Explanations

    dura

    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
    ViewFeatures
    -0.51
     виправивши
    -0.44
    ⓧ
    -0.44
     brancas
    -0.43
    Responder
    -0.43
    blurRadius
    -0.42
    createCanvas
    -0.41
    windowFixed
    -0.41
     esimer
    -0.40
    astéroïdes
    -0.40
    POSITIVE LOGITS
    DataPropertyName
    0.64
     Sheet
    0.58
    providedIn
    0.57
     AttributeSet
    0.57
    Portale
    0.57
    <bos>
    0.57
     Si
    0.56
     createState
    0.56
    ImageContext
    0.54
     lif
    0.53
    Activations Density 0.004%

    No Known Activations