© 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. 0-CLT-HP
    7. 43202
    Prev
    Next
    INDEX
    Explanations

    shop

    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
    grunns
    -0.71
    CloseOperation
    -0.70
    VersionUID
    -0.69
     estimés
    -0.68
     createSlice
    -0.66
    ########.
    -0.66
    <?>>
    -0.65
    saraba
    -0.64
    활
    -0.64
    ++]=
    -0.64
    POSITIVE LOGITS
    ial
    0.50
    ,
    0.47
    ám
    0.44
     bá
    0.44
    Technic
    0.41
     oficial
    0.41
     minor
    0.41
    offic
    0.40
     Pem
    0.40
     AssemblyTitle
    0.40
    Activations Density 0.146%

    No Known Activations