© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3140
    Prev
    Next
    INDEX
    Explanations

    such

    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
    )++;
    -0.78
     Efq
    -0.74
     avoient
    -0.73
    ]++;
    -0.69
     étoient
    -0.68
     RIPRODUZIONE
    -0.67
    classmethod
    -0.65
     plainte
    -0.65
     uſe
    -0.64
    ŚĆ
    -0.63
    POSITIVE LOGITS
     with
    0.64
    OGND
    0.56
    with
    0.51
     in
    0.50
    AndEndTag
    0.47
     通販
    0.46
    原始内容存档于
    0.44
     at
    0.43
    ない
    0.43
     for
    0.43
    Activations Density 0.004%

    No Known Activations