© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 982
    Prev
    Next
    INDEX
    Explanations

    found/when

    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
    found
    -0.67
     found
    -0.64
    s
    -0.63
    al
    -0.58
    es
    -0.58
    ar
    -0.55
    am
    -0.54
    u
    -0.54
    is
    -0.53
    or
    -0.52
    POSITIVE LOGITS
    ########.
    0.87
     '\\;'
    0.85
    ]")]
    0.78
     Efq
    0.75
     licks
    0.74
    #+#
    0.72
    StoryboardSegue
    0.71
    ImageContext
    0.70
    يميديا
    0.69
    encodeWith
    0.69
    Activations Density 0.063%

    No Known Activations