© 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. 0-CLT-HP
    4. 45055
    Prev
    Next
    INDEX
    Explanations

    un

    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
     le
    -0.78
     un
    -0.73
     l
    -0.69
     de
    -0.69
     a
    -0.68
     la
    -0.65
     les
    -0.61
     per
    -0.59
     il
    -0.59
     para
    -0.59
    POSITIVE LOGITS
     Vikipedi
    0.96
     étoient
    0.96
     auroit
    0.84
     hâte
    0.84
    (!__
    0.84
     avoient
    0.83
     espagne
    0.83
     pouvoit
    0.82
     étoit
    0.82
     feroit
    0.82
    Activations Density 0.076%

    No Known Activations