© 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. 13529
    Prev
    Next
    INDEX
    Explanations

    lical

    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
     originaux
    -0.71
     majeurs
    -0.69
     kaynağından
    -0.67
     étrangères
    -0.66
     africains
    -0.65
     prêts
    -0.65
     Yom
    -0.65
     femenina
    -0.65
     femminile
    -0.64
     Differenz
    -0.64
    POSITIVE LOGITS
     iprot
    0.52
    tagHelperRunner
    0.51
    stdc
    0.51
    })`
    0.48
     die
    0.47
    getSystemService
    0.45
     Ter
    0.45
     Roll
    0.45
     ‘
    0.45
     car
    0.44
    Activations Density 0.011%

    No Known Activations