© 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. 5-CLT-HP
    7. 97162
    Prev
    Next
    INDEX
    Explanations

    intersections and roads

    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
     TextInputType
    -0.45
    шк
    -0.44
    scan
    -0.44
     evin
    -0.42
    かわ
    -0.42
    弦
    -0.41
    投
    -0.41
     eins
    -0.40
     Annual
    -0.39
    CHK
    -0.39
    POSITIVE LOGITS
     EconPapers
    0.80
     дописавши
    0.75
    EndGlobalSection
    0.72
     мәкал
    0.70
    RegistryLite
    0.67
    #
    0.65
    DockStyle
    0.64
    uxxxx
    0.63
    +#+
    0.61
     nemlig
    0.60
    Activations Density 0.020%

    No Known Activations