© 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. 20-CLT-HP
    7. 72704
    Prev
    Next
    INDEX
    Explanations

    Sam

    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
    onAttach
    -0.57
    URLException
    -0.56
     AssemblyCulture
    -0.51
     ComVisible
    -0.50
     CiNii
    -0.47
     صوتيه
    -0.46
    nofollow
    -0.44
     StringTokenizer
    -0.43
     propOrder
    -0.42
     Sosial
    -0.41
    POSITIVE LOGITS
     autorytatywna
    0.63
    AxisAlignment
    0.55
    Autoritní
    0.53
     henvisninger
    0.50
    riffen
    0.49
    ContentAsync
    0.49
    gemeester
    0.48
    makeConstraints
    0.47
    rona
    0.47
    tub
    0.47
    Activations Density 0.001%

    No Known Activations