© 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. 1-CLT-HP
    7. 15305
    Prev
    Next
    INDEX
    Explanations

    iling

    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
    styleType
    -0.60
    SBATCH
    -0.58
    脚注の使い方
    -0.54
    #+#
    -0.53
     prega
    -0.52
    Архівовано
    -0.52
    PrototypeOf
    -0.52
    complexContent
    -0.51
     تعدى
    -0.50
    idosis
    -0.49
    POSITIVE LOGITS
    ("}");
    0.54
    cerna
    0.52
    IVer
    0.51
    فظ
    0.50
    adpleegd
    0.50
    ContentAsync
    0.48
    اژ
    0.47
    ftar
    0.47
    eqref
    0.46
    VER
    0.45
    Activations Density 0.041%

    No Known Activations