© 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. 4-CLT-HP
    7. 1047
    Prev
    Next
    INDEX
    Explanations

    2

    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
     plano
    -0.48
    tiftung
    -0.47
    ginine
    -0.44
     ра
    -0.43
    context
    -0.43
    fromCharCode
    -0.42
    pasto
    -0.41
     voler
    -0.41
    ")->
    -0.41
     componenti
    -0.40
    POSITIVE LOGITS
    EndContext
    0.79
    AddHtmlAttribute
    0.73
    StructEnd
    0.64
    Personendaten
    0.63
    enumii
    0.63
    buttonBar
    0.63
     AssemblyCompany
    0.61
     Meksiku
    0.60
     متعلقه
    0.60
    awtextra
    0.58
    Activations Density 0.000%

    No Known Activations