© 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. 1-CLT-HP
    7. 15029
    Prev
    Next
    INDEX
    Explanations

    latent

    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
     Signalez
    -0.61
     latter
    -0.45
    antaine
    -0.43
    lería
    -0.43
     OMIT
    -0.43
    Datuak
    -0.43
    før
    -0.43
    unicaciones
    -0.43
    republik
    -0.43
    Ainsi
    -0.43
    POSITIVE LOGITS
     '\\;'
    0.68
    égard
    0.55
    
    0.54
     Efq
    0.53
     Wikiseite
    0.53
     dignité
    0.52
     RIPRODUZIONE
    0.51
    createCanvas
    0.50
    stdc
    0.50
     ſever
    0.50
    Activations Density 0.010%

    No Known Activations