© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93965
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    EndContext
    -0.60
    ImageContext
    -0.56
     виправивши
    -0.54
    __':
    -0.47
    styleType
    -0.46
    
    -0.45
     تكبرها
    -0.44
    __':
    -0.44
    
    -0.44
     سكانية
    -0.43
    POSITIVE LOGITS
    2
    1.09
    1
    1.05
    6
    1.03
    3
    1.01
    4
    1.01
    5
    0.98
    8
    0.96
    7
    0.96
    9
    0.95
    0
    0.88
    Activations Density 0.389%

    No Known Activations