© 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. 5-CLT-HP
    7. 2198
    Prev
    Next
    INDEX
    Explanations

    webpage text excerpts

    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
     grà
    -0.48
    tvguidetime
    -0.39
    isition
    -0.38
    m
    -0.37
    pośred
    -0.37
    Ceci
    -0.37
    gom
    -0.36
    zystać
    -0.36
     class
    -0.35
    druid
    -0.35
    POSITIVE LOGITS
    TagMode
    1.03
    #+#
    0.94
    +#+#
    0.84
    Autoritní
    0.75
    出版年
    0.75
     nakalista
    0.74
    extAlignment
    0.71
     propOrder
    0.70
    +#+
    0.70
    PerformLayout
    0.70
    Activations Density 0.000%

    No Known Activations