© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43898
    Prev
    Next
    INDEX
    Explanations

    free

    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
     free
    -1.69
    free
    -1.45
    Free
    -1.44
     Free
    -1.41
    FREE
    -1.23
     FREE
    -1.22
     freie
    -1.10
     freien
    -1.09
     libres
    -1.05
     librement
    -0.95
    POSITIVE LOGITS
     to
    0.59
    GEBURTSDATUM
    0.56
    StoryboardSegue
    0.55
    hand
    0.55
    SourceChecksum
    0.53
    hoodie
    0.50
    发表于
    0.49
    AddHtmlAttribute
    0.49
    form
    0.45
    time
    0.43
    Activations Density 0.233%

    No Known Activations