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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2636
    Prev
    Next
    INDEX
    Explanations

    as

    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
    rungsseite
    -0.81
    SequentialGroup
    -0.72
    ValueStyle
    -0.71
    ']")
    -0.65
    BeginContext
    -0.62
     يتيمه
    -0.60
    }],
    -0.60
     ?>
    -0.59
    NameInMap
    -0.59
    AndEndTag
    -0.58
    POSITIVE LOGITS
     one
    0.57
     captain
    0.56
     director
    0.56
     CEO
    0.55
     editor
    0.54
     president
    0.54
     mayor
    0.54
    :+:
    0.51
     vice
    0.50
     head
    0.50
    Activations Density 0.003%

    No Known Activations