© 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. 0-CLT-HP
    7. 93158
    Prev
    Next
    INDEX
    Explanations

    agglomer

    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
     branche
    -0.47
     AssemblyTitle
    -0.45
     Allein
    -0.42
     terras
    -0.41
    skim
    -0.39
    рки
    -0.39
    harap
    -0.38
    λα
    -0.37
    cking
    -0.36
     diffuse
    -0.36
    POSITIVE LOGITS
     ligiloj
    0.90
    AndEndTag
    0.83
     NUKAT
    0.81
     resourceCulture
    0.80
    contentLoaded
    0.80
    Geplaatst
    0.80
     betweenstory
    0.78
    \{\\
    0.77
    __':
    0.77
    ViewFeatures
    0.76
    Activations Density 0.899%

    No Known Activations