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. 4-CLT-HP
    4. 3953
    Prev
    Next
    INDEX
    Explanations

    identification or lack thereof

    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
    ImageContext
    -0.63
    Hozzáférés
    -0.62
     <<<<<<<<<<<<<<
    -0.60
    abestanden
    -0.54
    IsMutable
    -0.49
     مشين
    -0.49
    InjectAttribute
    -0.49
    VITA
    -0.48
     насељу
    -0.47
    ystis
    -0.46
    POSITIVE LOGITS
     Flying
    0.65
     âgées
    0.58
     drôle
    0.58
    ToMany
    0.54
    }))
    
    0.54
     Lander
    0.53
    ")));
    
    0.53
     flying
    0.53
    Flying
    0.53
    )))));
    0.53
    Activations Density 0.010%

    No Known Activations