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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13549
    Prev
    Next
    INDEX
    Explanations

    as

    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
     يتيمه
    -0.82
    featureID
    -0.75
    ValueStyle
    -0.69
    RenderAtEndOf
    -0.69
    ')));
    -0.66
    bewerken
    -0.66
     bezeichneter
    -0.64
     AssemblyCompany
    -0.64
     NSCoder
    -0.63
    Datuak
    -0.61
    POSITIVE LOGITS
     uncin
    0.53
     ejus
    0.51
     conveyance
    0.48
    Pio
    0.48
     daytime
    0.47
     spoken
    0.46
     scap
    0.46
     Ferenc
    0.45
     spaghetti
    0.45
     uncertain
    0.44
    Activations Density 0.005%

    No Known Activations