© 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. 4-CLT-HP
    7. 1700
    Prev
    Next
    INDEX
    Explanations

    ums

    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
    complexType
    -0.56
    SequentialGroup
    -0.50
    unchecked
    -0.50
     BoxFit
    -0.49
     Stern
    -0.47
    divers
    -0.46
    UTERS
    -0.46
     layui
    -0.46
    乓
    -0.45
    ("~/
    -0.45
    POSITIVE LOGITS
    %)$
    0.76
    Хьажоргаш
    0.75
    LookAnd
    0.71
    MessageOf
    0.60
     Jefus
    0.59
     gawas
    0.58
    ConstraintMaker
    0.58
    Sklici
    0.55
    новниш
    0.54
    клопе
    0.54
    Activations Density 0.002%

    No Known Activations