© 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. 90733
    Prev
    Next
    INDEX
    Explanations

    required

    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
     forced
    -1.84
    forced
    -1.81
     Forced
    -1.63
    Forced
    -1.52
     compelled
    -1.26
     obliged
    -1.19
     enforced
    -1.16
     compulsory
    -1.09
     obligado
    -0.99
     mandatory
    -0.98
    POSITIVE LOGITS
    StoryboardSegue
    0.73
    Lähteet
    0.73
     to
    0.72
    SharedDtor
    0.72
     الرياضيه
    0.71
    zzleHttp
    0.71
    principalColumn
    0.70
     HttpHeaders
    0.69
     ProtoMessage
    0.68
     Wikimedijinoj
    0.66
    Activations Density 0.855%

    No Known Activations