© 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. 20-CLT-HP
    7. 73682
    Prev
    Next
    INDEX
    Explanations

    Code/Social media posts

    np_max-act-logits · 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
    PageFactory
    -0.67
     defaultstate
    -0.58
    +#+
    -0.56
    Viitteet
    -0.54
    EndContext
    -0.51
     getRule
    -0.50
    UIControlState
    -0.50
    AutoScale
    -0.49
     Référence
    -0.48
    CGRectMake
    -0.48
    POSITIVE LOGITS
     utafitiHapana
    0.68
    Pe
    0.56
     Peoples
    0.56
    ImageContext
    0.53
     People
    0.53
    P
    0.51
    
    0.51
     Prisoner
    0.51
     letting
    0.50
    GeneratedMessage
    0.49
    Activations Density 0.000%

    No Known Activations