© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4410
    Prev
    Next
    INDEX
    Explanations

    indicate

    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
     تانيه
    -1.09
    +#+#
    -1.06
     متعلقه
    -0.94
     تضيفلها
    -0.91
     سكانية
    -0.88
    AnimationsModule
    -0.87
    principalColumn
    -0.85
     resourceCulture
    -0.84
    tagHelperRunner
    -0.84
    AndEndTag
    -0.83
    POSITIVE LOGITS
     that
    0.74
     a
    0.57
     you
    0.56
     dass
    0.53
    that
    0.49
     que
    0.48
     when
    0.48
     which
    0.47
     there
    0.45
     lo
    0.44
    Activations Density 0.002%

    No Known Activations