© 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. 5-CLT-HP
    7. 93675
    Prev
    Next
    INDEX
    Explanations

    Digestion/bowel movement

    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
    
    -0.69
    tagHelperRunner
    -0.63
     виправивши
    -0.63
    WithIOException
    -0.62
     Biôgrafia
    -0.62
    ]._
    -0.60
    MessageOf
    -0.59
    ագրություններ
    -0.59
    /**
    -0.58
    Datuak
    -0.57
    POSITIVE LOGITS
    ponses
    0.59
     scolaires
    0.56
     financières
    0.54
     alimentaires
    0.51
    +#+
    0.49
    bedrijf
    0.49
     WebDriverWait
    0.49
     Battista
    0.47
     horaire
    0.46
     secondaires
    0.43
    Activations Density 0.000%

    No Known Activations