© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 740
    Prev
    Next
    INDEX
    Explanations

    anna

    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
     NOAA
    -0.63
    NOAA
    -0.58
    AsStream
    -0.55
     Carroll
    -0.53
    ירת
    -0.53
    YMS
    -0.49
    utched
    -0.47
     дописавши
    -0.46
    nant
    -0.46
    WebMethod
    -0.46
    POSITIVE LOGITS
     &___
    0.69
    PrototypeOf
    0.55
    MENAFN
    0.54
     jspb
    0.54
     torus
    0.52
     gyrus
    0.52
    zzleHttp
    0.51
    NSUserDefaults
    0.51
     viri
    0.50
     entrain
    0.50
    Activations Density 0.020%

    No Known Activations