© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45550
    Prev
    Next
    INDEX
    Explanations

    HSP

    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
    Alike
    -1.15
     HSP
    -0.99
    HSP
    -0.82
    otropic
    -0.67
    igia
    -0.54
    AutoScale
    -0.50
     Siena
    -0.49
     hits
    -0.47
    Datagram
    -0.47
     Claremont
    -0.47
    POSITIVE LOGITS
    GEBURTSDATUM
    0.63
    )}
    0.57
    ("}");
    0.56
    ]**
    0.55
    caud
    0.54
     ***!
    0.53
     ricerca
    0.52
    }~
    0.52
     navigazione
    0.52
    ölkerung
    0.51
    Activations Density 0.047%

    No Known Activations