© 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. 3473
    Prev
    Next
    INDEX
    Explanations

    language codes

    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
     race
    -0.56
    jfree
    -0.56
     cam
    -0.54
    Glej
    -0.54
    RunAsync
    -0.54
    umé
    -0.53
    tsch
    -0.53
    ngdoc
    -0.52
    ÇO
    -0.52
     semp
    -0.51
    POSITIVE LOGITS
     snippetHide
    0.60
     prácti
    0.59
     surla
    0.47
     **/
    0.46
    middels
    0.46
    }}^
    0.46
     specifico
    0.45
     referrerpolicy
    0.45
     veckor
    0.44
    ırlar
    0.44
    Activations Density 0.009%

    No Known Activations