© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73636
    Prev
    Next
    INDEX
    Explanations

    Mixed content texts

    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
    SharedDtor
    -0.83
     Италијани
    -0.81
     Efq
    -0.77
    SharedCtor
    -0.76
     quæ
    -0.75
     '\\;'
    -0.75
     resourceCulture
    -0.74
    writeFieldEnd
    -0.71
     avoient
    -0.70
    ]='\
    -0.69
    POSITIVE LOGITS
     mark
    0.78
     AttributeSet
    0.47
    pides
    0.39
    setImageBitmap
    0.39
     stake
    0.38
    enciaga
    0.38
     vs
    0.37
     …
    0.37
     the
    0.36
     Mark
    0.36
    Activations Density 0.000%

    No Known Activations