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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93423
    Prev
    Next
    INDEX
    Explanations

    go

    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
     go
    -0.68
     it
    -0.57
    go
    -0.54
     going
    -0.54
     raise
    -0.52
     went
    -0.50
     the
    -0.50
     goes
    -0.49
     increase
    -0.49
     be
    -0.48
    POSITIVE LOGITS
    <bos>
    0.79
    Rüyada
    0.79
     Chwiliwch
    0.64
     itſelf
    0.64
     tarko
    0.63
    mobileqq
    0.62
    ￡
    0.61
    }();
    0.60
     thither
    0.60
     {},
    0.60
    Activations Density 0.030%

    No Known Activations