© 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. 5-CLT-HP
    7. 92031
    Prev
    Next
    INDEX
    Explanations

    assurance

    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
     <>",
    -0.60
     actionMode
    -0.55
     "..\..\..\
    -0.53
     "..\..\
    -0.53
    utnant
    -0.52
    detta
    -0.49
    tableFuture
    -0.48
    posedge
    -0.47
    AMENTE
    -0.47
    Autoritní
    -0.47
    POSITIVE LOGITS
     متعلقه
    0.71
    RenderAtEndOf
    0.58
    曖昧さ回避
    0.57
    ValueStyle
    0.56
    Бахар
    0.56
     '/';
    0.54
    createTextNode
    0.52
    amię
    0.51
     beginnetje
    0.50
     of
    0.49
    Activations Density 0.005%

    No Known Activations