Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73826
    Prev
    Next
    INDEX
    Explanations

    Heroes

    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
     يتيمه
    -1.06
    +#+#
    -0.96
    Geplaatst
    -0.92
    Rhestr
    -0.91
    afficheront
    -0.90
     BrowserModule
    -0.88
     препратки
    -0.87
    tvguidetime
    -0.87
    nestjs
    -0.84
     ProtoMessage
    -0.84
    POSITIVE LOGITS
     Heroes
    0.61
    Heroes
    0.47
     heroes
    0.46
    Conne
    0.43
     Guests
    0.42
     hero
    0.41
     R
    0.41
     gi
    0.40
     Families
    0.40
    heroes
    0.39
    Activations Density 0.000%

    No Known Activations