© 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. 91275
    Prev
    Next
    INDEX
    Explanations

    What, Which

    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
    oredCriteria
    -0.84
    tagHelperRunner
    -0.82
    UnsafeEnabled
    -0.60
    Jereo
    -0.59
    lorette
    -0.55
    EndGlobalSection
    -0.55
    NameInMap
    -0.55
    StoryboardSegue
    -0.54
     BoxFit
    -0.54
    enumi
    -0.53
    POSITIVE LOGITS
    ))));
    0.58
    >({
    0.50
     صوتيه
    0.47
    )))));
    0.47
    </h1>
    0.46
    SizeF
    0.43
     steps
    0.43
    ERVER
    0.43
    
    0.42
    Erfolge
    0.42
    Activations Density 0.023%

    No Known Activations