© 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. 73726
    Prev
    Next
    INDEX
    Explanations

    radio

    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
     bio
    -0.57
    RestTemplate
    -0.53
     hours
    -0.51
    zino
    -0.51
     depth
    -0.49
    rawDesc
    -0.49
     Hours
    -0.48
     resolving
    -0.46
    "]).
    -0.46
    ništvo
    -0.46
    POSITIVE LOGITS
     camiset
    0.56
     disambiguazione
    0.52
    يكب
    0.51
     صوتيه
    0.50
    GrantedAuthority
    0.50
    ISupport
    0.50
    новниш
    0.49
    Nazionale
    0.49
    amssymb
    0.48
    Istorija
    0.48
    Activations Density 0.002%

    No Known Activations